% WP-AI-0001 — references whose identifier, title, authors and date were verified against the arXiv API on 2026-11-09.
% primaryClass is not verified field-by-field; venue information (NeurIPS/ICML/ICLR/JMLR) is NOT included unless verified separately.
% Do not add entries to this file without verification; unverified candidates go to references_unverified.md.

@misc{achara2026multi,
  title        = {{Multi-Way Representation Alignment}},
  author       = {Akshit Achara and Tatiana Gaintseva and Mateo Mahaut and Pritish Chakraborty and Viktor Stenby Johansson and Melih Barsbey and Emanuele Rodolà and Donato Crisostomi},
  year         = {2026},
  month        = {2},
  eprint       = {2602.06205},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2602.06205},
  note         = {arXiv:2602.06205; metadata verified via arXiv API on 2026-11-09}
}

@misc{agarwal2026cross,
  title        = {{Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study}},
  author       = {Ayushi Agarwal},
  year         = {2026},
  month        = {5},
  eprint       = {2608.05164},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2608.05164},
  note         = {arXiv:2608.05164; metadata verified via arXiv API on 2026-11-09}
}

@misc{ainsworth2022git,
  title        = {{Git Re-Basin: Merging Models modulo Permutation Symmetries}},
  author       = {Samuel K. Ainsworth and Jonathan Hayase and Siddhartha Srinivasa},
  year         = {2022},
  month        = {9},
  eprint       = {2209.04836},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2209.04836},
  note         = {arXiv:2209.04836; metadata verified via arXiv API on 2026-11-09}
}

@misc{bansal2021revisiting,
  title        = {{Revisiting Model Stitching to Compare Neural Representations}},
  author       = {Yamini Bansal and Preetum Nakkiran and Boaz Barak},
  year         = {2021},
  month        = {6},
  eprint       = {2106.07682},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2106.07682},
  note         = {arXiv:2106.07682; metadata verified via arXiv API on 2026-11-09}
}

@misc{chen2025transferring,
  title        = {{Transferring Linear Features Across Language Models With Model Stitching}},
  author       = {Alan Chen and Jack Merullo and Alessandro Stolfo and Ellie Pavlick},
  year         = {2025},
  month        = {6},
  eprint       = {2506.06609},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2506.06609},
  note         = {arXiv:2506.06609; metadata verified via arXiv API on 2026-11-09}
}

@misc{conmy2023towards,
  title        = {{Towards Automated Circuit Discovery for Mechanistic Interpretability}},
  author       = {Arthur Conmy and Augustine N. Mavor-Parker and Aengus Lynch and Stefan Heimersheim and Adrià Garriga-Alonso},
  year         = {2023},
  month        = {4},
  eprint       = {2304.14997},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2304.14997},
  note         = {arXiv:2304.14997; metadata verified via arXiv API on 2026-11-09}
}

@misc{cristofano2026universal,
  title        = {{Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction}},
  author       = {Tony Cristofano},
  year         = {2026},
  month        = {1},
  eprint       = {2601.16034},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2601.16034},
  note         = {arXiv:2601.16034; metadata verified via arXiv API on 2026-11-09}
}

@misc{cunningham2023sparse,
  title        = {{Sparse Autoencoders Find Highly Interpretable Features in Language Models}},
  author       = {Hoagy Cunningham and Aidan Ewart and Logan Riggs and Robert Huben and Lee Sharkey},
  year         = {2023},
  month        = {9},
  eprint       = {2309.08600},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2309.08600},
  note         = {arXiv:2309.08600; metadata verified via arXiv API on 2026-11-09}
}

@misc{fan2026training,
  title        = {{Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning}},
  author       = {Jiahe Fan and Si Chen and Yinghao Hou and Aiyuan Zhang and Hong Xie},
  year         = {2026},
  month        = {7},
  eprint       = {2608.13596},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2608.13596},
  note         = {arXiv:2608.13596; metadata verified via arXiv API on 2026-11-09}
}

@misc{geiger2023causal,
  title        = {{Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability}},
  author       = {Atticus Geiger and Duligur Ibeling and Amir Zur and Maheep Chaudhary and Sonakshi Chauhan and Jing Huang and Aryaman Arora and Zhengxuan Wu and Noah Goodman and Christopher Potts and Thomas Icard},
  year         = {2023},
  month        = {1},
  eprint       = {2301.04709},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2301.04709},
  note         = {arXiv:2301.04709; metadata verified via arXiv API on 2026-11-09}
}

@misc{geiger2023finding,
  title        = {{Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations}},
  author       = {Atticus Geiger and Zhengxuan Wu and Christopher Potts and Thomas Icard and Noah D. Goodman},
  year         = {2023},
  month        = {3},
  eprint       = {2303.02536},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2303.02536},
  note         = {arXiv:2303.02536; metadata verified via arXiv API on 2026-11-09}
}

@misc{gu2025beyond,
  title        = {{Beyond Neural Incompatibility: Cross-Scale Knowledge Transfer in Language Models through Latent Semantic Alignment}},
  author       = {Jian Gu and Aldeida Aleti and Chunyang Chen and Hongyu Zhang},
  year         = {2025},
  month        = {10},
  eprint       = {2510.24208},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2510.24208},
  note         = {arXiv:2510.24208; metadata verified via arXiv API on 2026-11-09}
}

@misc{gurnee2023finding,
  title        = {{Finding Neurons in a Haystack: Case Studies with Sparse Probing}},
  author       = {Wes Gurnee and Neel Nanda and Matthew Pauly and Katherine Harvey and Dmitrii Troitskii and Dimitris Bertsimas},
  year         = {2023},
  month        = {5},
  eprint       = {2305.01610},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2305.01610},
  note         = {arXiv:2305.01610; metadata verified via arXiv API on 2026-11-09}
}

@misc{hendel2023context,
  title        = {{In-Context Learning Creates Task Vectors}},
  author       = {Roee Hendel and Mor Geva and Amir Globerson},
  year         = {2023},
  month        = {10},
  eprint       = {2310.15916},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2310.15916},
  note         = {arXiv:2310.15916; metadata verified via arXiv API on 2026-11-09}
}

@misc{hernandez2023linearity,
  title        = {{Linearity of Relation Decoding in Transformer Language Models}},
  author       = {Evan Hernandez and Arnab Sen Sharma and Tal Haklay and Kevin Meng and Martin Wattenberg and Jacob Andreas and Yonatan Belinkov and David Bau},
  year         = {2023},
  month        = {8},
  eprint       = {2308.09124},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2308.09124},
  note         = {arXiv:2308.09124; metadata verified via arXiv API on 2026-11-09}
}

@misc{huh2024platonic,
  title        = {{The Platonic Representation Hypothesis}},
  author       = {Minyoung Huh and Brian Cheung and Tongzhou Wang and Phillip Isola},
  year         = {2024},
  month        = {5},
  eprint       = {2405.07987},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2405.07987},
  note         = {arXiv:2405.07987; metadata verified via arXiv API on 2026-11-09}
}

@misc{ilharco2022editing,
  title        = {{Editing Models with Task Arithmetic}},
  author       = {Gabriel Ilharco and Marco Tulio Ribeiro and Mitchell Wortsman and Suchin Gururangan and Ludwig Schmidt and Hannaneh Hajishirzi and Ali Farhadi},
  year         = {2022},
  month        = {12},
  eprint       = {2212.04089},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2212.04089},
  note         = {arXiv:2212.04089; metadata verified via arXiv API on 2026-11-09}
}

@misc{kim2026one,
  title        = {{One Adapter Pair per Model: A Universal Activation Interface for Language Models}},
  author       = {Su-Hyeon Kim and Jiwan Mun and Yo-Sub Han},
  year         = {2026},
  month        = {8},
  eprint       = {2608.09521},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2608.09521},
  note         = {arXiv:2608.09521; metadata verified via arXiv API on 2026-11-09}
}

@misc{kornblith2019similarity,
  title        = {{Similarity of Neural Network Representations Revisited}},
  author       = {Simon Kornblith and Mohammad Norouzi and Honglak Lee and Geoffrey Hinton},
  year         = {2019},
  month        = {5},
  eprint       = {1905.00414},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/1905.00414},
  note         = {arXiv:1905.00414; metadata verified via arXiv API on 2026-11-09}
}

@misc{lan2024quantifying,
  title        = {{Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders}},
  author       = {Michael Lan and Philip Torr and Austin Meek and Ashkan Khakzar and David Krueger and Fazl Barez},
  year         = {2024},
  month        = {10},
  eprint       = {2410.06981},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2410.06981},
  note         = {arXiv:2410.06981; metadata verified via arXiv API on 2026-11-09}
}

@misc{lee2025shared,
  title        = {{Shared Global and Local Geometry of Language Model Embeddings}},
  author       = {Andrew Lee and Melanie Weber and Fernanda Viégas and Martin Wattenberg},
  year         = {2025},
  month        = {3},
  eprint       = {2503.21073},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2503.21073},
  note         = {arXiv:2503.21073; metadata verified via arXiv API on 2026-11-09}
}

@misc{li2023inference,
  title        = {{Inference-Time Intervention: Eliciting Truthful Answers from a Language Model}},
  author       = {Kenneth Li and Oam Patel and Fernanda Viégas and Hanspeter Pfister and Martin Wattenberg},
  year         = {2023},
  month        = {6},
  eprint       = {2306.03341},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2306.03341},
  note         = {arXiv:2306.03341; metadata verified via arXiv API on 2026-11-09}
}

@misc{lo2024large,
  title        = {{Large Language Models Relearn Removed Concepts}},
  author       = {Michelle Lo and Shay B. Cohen and Fazl Barez},
  year         = {2024},
  month        = {1},
  eprint       = {2401.01814},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2401.01814},
  note         = {arXiv:2401.01814; metadata verified via arXiv API on 2026-11-09}
}

@misc{meng2022locating,
  title        = {{Locating and Editing Factual Associations in GPT}},
  author       = {Kevin Meng and David Bau and Alex Andonian and Yonatan Belinkov},
  year         = {2022},
  month        = {2},
  eprint       = {2202.05262},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2202.05262},
  note         = {arXiv:2202.05262; metadata verified via arXiv API on 2026-11-09}
}

@misc{minixhofer2024zero,
  title        = {{Zero-Shot Tokenizer Transfer}},
  author       = {Benjamin Minixhofer and Edoardo Maria Ponti and Ivan Vulić},
  year         = {2024},
  month        = {5},
  eprint       = {2405.07883},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2405.07883},
  note         = {arXiv:2405.07883; metadata verified via arXiv API on 2026-11-09}
}

@misc{nasirisarvi2025sparc,
  title        = {{SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability}},
  author       = {Ali Nasiri-Sarvi and Hassan Rivaz and Mahdi S. Hosseini},
  year         = {2025},
  month        = {7},
  eprint       = {2507.06265},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2507.06265},
  note         = {arXiv:2507.06265; metadata verified via arXiv API on 2026-11-09}
}

@misc{ognev2026sharedsae,
  title        = {{SharedSAE: One Feature Dictionary Across Language Models}},
  author       = {Daniil Ognev and Célian Vasson and Lijie Hu and Kentaro Inui and Benjamin Heinzerling},
  year         = {2026},
  month        = {9},
  eprint       = {2609.04344},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2609.04344},
  note         = {arXiv:2609.04344; metadata verified via arXiv API on 2026-11-09}
}

@misc{panigrahi2023task,
  title        = {{Task-Specific Skill Localization in Fine-tuned Language Models}},
  author       = {Abhishek Panigrahi and Nikunj Saunshi and Haoyu Zhao and Sanjeev Arora},
  year         = {2023},
  month        = {2},
  eprint       = {2302.06600},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2302.06600},
  note         = {arXiv:2302.06600; metadata verified via arXiv API on 2026-11-09}
}

@misc{raghu2017svcca,
  title        = {{SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability}},
  author       = {Maithra Raghu and Justin Gilmer and Jason Yosinski and Jascha Sohl-Dickstein},
  year         = {2017},
  month        = {6},
  eprint       = {1706.05806},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/1706.05806},
  note         = {arXiv:1706.05806; metadata verified via arXiv API on 2026-11-09}
}

@misc{sinii2025small,
  title        = {{Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors}},
  author       = {Viacheslav Sinii and Nikita Balagansky and Gleb Gerasimov and Daniil Laptev and Yaroslav Aksenov and Vadim Kurochkin and Alexey Gorbatovski and Boris Shaposhnikov and Daniil Gavrilov},
  year         = {2025},
  month        = {9},
  eprint       = {2509.06608},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2509.06608},
  note         = {arXiv:2509.06608; metadata verified via arXiv API on 2026-11-09}
}

@misc{sun2024massive,
  title        = {{Massive Activations in Large Language Models}},
  author       = {Mingjie Sun and Xinlei Chen and J. Zico Kolter and Zhuang Liu},
  year         = {2024},
  month        = {2},
  eprint       = {2402.17762},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2402.17762},
  note         = {arXiv:2402.17762; metadata verified via arXiv API on 2026-11-09}
}

@misc{thasarathan2025universal,
  title        = {{Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment}},
  author       = {Harrish Thasarathan and Julian Forsyth and Thomas Fel and Matthew Kowal and Konstantinos G. Derpanis},
  year         = {2025},
  month        = {2},
  eprint       = {2502.03714},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2502.03714},
  note         = {arXiv:2502.03714; metadata verified via arXiv API on 2026-11-09}
}

@misc{todd2023function,
  title        = {{Function Vectors in Large Language Models}},
  author       = {Eric Todd and Millicent L. Li and Arnab Sen Sharma and Aaron Mueller and Byron C. Wallace and David Bau},
  year         = {2023},
  month        = {10},
  eprint       = {2310.15213},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2310.15213},
  note         = {arXiv:2310.15213; metadata verified via arXiv API on 2026-11-09}
}

@misc{turner2023steering,
  title        = {{Steering Language Models With Activation Engineering}},
  author       = {Alexander Matt Turner and Lisa Thiergart and Gavin Leech and David Udell and Juan J. Vazquez and Ulisse Mini and Monte MacDiarmid},
  year         = {2023},
  month        = {8},
  eprint       = {2308.10248},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2308.10248},
  note         = {arXiv:2308.10248; metadata verified via arXiv API on 2026-11-09}
}

@misc{vig2020causal,
  title        = {{Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias}},
  author       = {Jesse Vig and Sebastian Gehrmann and Yonatan Belinkov and Sharon Qian and Daniel Nevo and Simas Sakenis and Jason Huang and Yaron Singer and Stuart Shieber},
  year         = {2020},
  month        = {4},
  eprint       = {2004.12265},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2004.12265},
  note         = {arXiv:2004.12265; metadata verified via arXiv API on 2026-11-09}
}

@misc{wang2022interpretability,
  title        = {{Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small}},
  author       = {Kevin Wang and Alexandre Variengien and Arthur Conmy and Buck Shlegeris and Jacob Steinhardt},
  year         = {2022},
  month        = {11},
  eprint       = {2211.00593},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2211.00593},
  note         = {arXiv:2211.00593; metadata verified via arXiv API on 2026-11-09}
}

@misc{yadav2023ties,
  title        = {{TIES-Merging: Resolving Interference When Merging Models}},
  author       = {Prateek Yadav and Derek Tam and Leshem Choshen and Colin Raffel and Mohit Bansal},
  year         = {2023},
  month        = {6},
  eprint       = {2306.01708},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2306.01708},
  note         = {arXiv:2306.01708; metadata verified via arXiv API on 2026-11-09}
}

@misc{zhang2026negative,
  title        = {{A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting}},
  author       = {Peiyan Zhang and Jason Xin},
  year         = {2026},
  month        = {6},
  eprint       = {2606.03280},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2606.03280},
  note         = {arXiv:2606.03280; metadata verified via arXiv API on 2026-11-09}
}

@misc{zou2023representation,
  title        = {{Representation Engineering: A Top-Down Approach to AI Transparency}},
  author       = {Andy Zou and Long Phan and Sarah Chen and James Campbell and Phillip Guo and Richard Ren and Alexander Pan and Xuwang Yin and Mantas Mazeika and Ann-Kathrin Dombrowski and Shashwat Goel and Nathaniel Li and Michael J. Byun and Zifan Wang and Alex Mallen and Steven Basart and Sanmi Koyejo and Dawn Song and Matt Fredrikson and J. Zico Kolter and Dan Hendrycks},
  year         = {2023},
  month        = {10},
  eprint       = {2310.01405},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  url          = {https://arxiv.org/abs/2310.01405},
  note         = {arXiv:2310.01405; metadata verified via arXiv API on 2026-11-09}
}