© 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. 21416
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     andre
    -0.11
     other
    -0.10
    -0.10
    <|reserved_200016|>
    -0.10
     for
    -0.10
    .html
    -0.09
     in
    -0.09
     mock
    -0.09
     can
    -0.09
     custom
    -0.09
    POSITIVE LOGITS
    outi
    0.10
    neemt
    0.09
    nemen
    0.09
    Linha
    0.09
     \(
    0.09
    истон
    0.09
     الأمة
    0.09
     Γ
    0.09
    ంలోని
    0.09
     Linha
    0.08
    Activations Density 0.028%

    No Known Activations