Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their stability, interpretability, and show their practical utility. Over 50% of the features remain consistent across random seeds, and reconstruction quality is preserved. SAE features capture general acoustic and semantic information as well as specific events, including environmental noises and paralinguistic sounds (e.g. laughter, whispering) and disentangle them effectively, requiring removal of only 19-27% of features to erase a concept. Feature steering reduces Whisper's false speech detections by 70% with negligible WER increase, demonstrating real-world applicability. Finally, we find SAE features correlated with human EEG activity during speech perception, indicating alignment with human neural processing. The code and checkpoints are available at https://github.com/audiosae/audiosae_demo.

翻译：稀疏自编码器（SAE）是解释神经表征的强大工具，但其在音频领域的应用仍待深入探索。我们在Whisper和HuBERT所有编码器层上训练SAE，对其稳定性、可解释性进行了全面评估，并展示了其实用价值。超过50%的特征在不同随机种子下保持稳定，且重建质量得以保持。SAE特征既能捕捉通用声学与语义信息，也能识别特定事件（包括环境噪声和副语言声音，如笑声、耳语），并能有效解耦这些特征——仅需移除19-27%的特征即可消除特定概念。通过特征调控，Whisper的虚假语音检测错误率降低70%，而词错误率仅微幅增加，证明了其实用价值。最后，我们发现SAE特征与人类在语音感知过程中的脑电活动具有相关性，表明其与人类神经处理机制存在对齐。代码与检查点已开源：https://github.com/audiosae/audiosae_demo。