@misc{wu2025axbench,
  title={AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders},
  author={Zhengxuan Wu and Aryaman Arora and Atticus Geiger and Zheng Wang and Jing Huang and Dan Jurafsky and Christopher D. Manning and Christopher Potts},
  year={2025},
  eprint={2501.17148},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2501.17148}
}