© 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. 99705
    Prev
    Next
    INDEX
    Explanations

    quick

    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
    (dialog
    -0.08
     interiors
    -0.08
     spä
    -0.07
     ugl
    -0.07
    嘴
    -0.07
     percor
    -0.07
    Webpack
    -0.07
    (Dialog
    -0.07
    िभ
    -0.07
    ilean
    -0.07
    POSITIVE LOGITS
     Welcome
    0.09
    精选
    0.09
    ▼
    0.09
    Welcome
    0.09
     destacados
    0.08
     സ്വാഗത
    0.08
    Bienvenue
    0.08
     автоб
    0.08
     actionable
    0.08
     жит
    0.08
    Activations Density 0.016%

    No Known Activations