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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 113747
    Prev
    Next
    INDEX
    Explanations

    missing parentheses or brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humili
    -0.09
     AP
    -0.08
     unfair
    -0.08
     prefer
    -0.08
    -0.08
     Powers
    -0.08
     CPC
    -0.08
     Knowledge
    -0.08
     Rau
    -0.07
    _API
    -0.07
    POSITIVE LOGITS
     종료
    0.16
    关闭
    0.15
     закры
    0.15
    结束
    0.14
    終了
    0.14
    Closing
    0.14
     समाप्त
    0.13
     پایان
    0.13
     closing
    0.13
     fermeture
    0.13
    Activations Density 0.008%
    No Known Activations