© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45244
    Prev
    Next
    INDEX
    Explanations

    JWT

    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
    Color
    -0.09
    ardır
    -0.08
     >>=
    -0.08
    quire
    -0.08
    color
    -0.08
    _fold
    -0.08
    _color
    -0.08
     color
    -0.07
    .color
    -0.07
    .tip
    -0.07
    POSITIVE LOGITS
    (namespace
    0.09
     نطاق
    0.08
    	job
    0.08
     Horizon
    0.08
    ttet
    0.08
     horizon
    0.08
     dash
    0.08
    \Domain
    0.08
     Neto
    0.08
    hostname
    0.07
    Activations Density 0.003%

    No Known Activations