© 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. 11-RESID-POST-AA
    11. 94564
    Prev
    Next
    INDEX
    Explanations

    References to books and people

    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
     Hinweise
    -0.09
    iječ
    -0.09
    动画
    -0.08
    òg
    -0.08
    rtype
    -0.08
    _customize
    -0.08
    折
    -0.08
    偿
    -0.07
     Deals
    -0.07
     pinnacle
    -0.07
    POSITIVE LOGITS
     Beck
    0.09
     Paul
    0.08
     August
    0.08
     Pavel
    0.08
     Assad
    0.08
     Garcia
    0.08
     кай
    0.08
     trim
    0.08
     Kyle
    0.08
    546
    0.08
    Activations Density 0.010%

    No Known Activations