© 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. 19-RESID-POST-AA
    11. 19136
    Prev
    Next
    INDEX
    Explanations

    Physics equations

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drie
    -0.08
     khá
    -0.08
     thất
    -0.08
     ಬೆ
    -0.07
     cinq
    -0.07
    級
    -0.07
     rất
    -0.07
     poup
    -0.07
    _for
    -0.07
     stvari
    -0.07
    POSITIVE LOGITS
    linkplain
    0.10
    ής
    0.09
     appealing
    0.08
    Supply
    0.08
    Вс
    0.08
    相关新闻
    0.08
    관련
    0.08
     strongest
    0.08
     Gefahr
    0.08
    Avail
    0.08
    Activations Density 0.000%

    No Known Activations