© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5437
    Prev
    Next
    INDEX
    Explanations

    美

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    821
    -0.07
    932
    -0.07
    wick
    -0.07
    मन
    -0.07
    683
    -0.07
    영상
    -0.07
    premium
    -0.07
    653
    -0.07
    284
    -0.07
    क्रम
    -0.07
    POSITIVE LOGITS
    丽
    0.10
    麗
    0.10
    ಳು
    0.09
    ړې
    0.09
     малы
    0.09
    彩�
    0.09
    ющ
    0.09
    ющими
    0.09
    ಳೆಯ
    0.09
     largas
    0.09
    Activations Density 0.001%

    No Known Activations