© 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 EvalsExportsinterp-engineNEWAPI 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. 70136
    Prev
    Next
    INDEX
    Explanations

    policy

    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
     burocr
    -0.09
     بورس
    -0.08
    Lleg
    -0.08
    .blog
    -0.08
     cale
    -0.08
    BCD
    -0.08
     βα
    -0.08
     arreg
    -0.07
     柏
    -0.07
    .Bank
    -0.07
    POSITIVE LOGITS
    禁止
    0.10
     prohibited
    0.10
     запрещ
    0.10
    は禁止
    0.09
     banned
    0.09
     prohibits
    0.08
     개인정보
    0.08
     Allowed
    0.08
     misinformation
    0.08
    违规
    0.08
    Activations Density 0.011%

    No Known Activations