@article{interpretablerewardmodelviasparseautoenc,
  title = {Interpretable Reward Model via Sparse Autoencoder},
  author = {Shuyi Zhang and Wei Shi and Sihang Li and Jiayi Liao and Hengxing Cai and Xiang Wang},
  year = {2025},
  eprint = {2508.08746},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.08746},
}