@article{interpretabilityillusionswithsparse,
  title = {Interpretability Illusions with Sparse Autoencoders: Evaluating Robustness of Concept Representations},
  author = {Aaron J. Li and Suraj Srinivas and Usha Bhalla and Himabindu Lakkaraju},
  year = {2025},
  eprint = {2505.16004},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.16004v1},
}