© 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. 108608
    Prev
    Next
    INDEX
    Explanations

    $

    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
     excit
    -0.08
    -conditioning
    -0.07
    (slice
    -0.07
    _hook
    -0.07
     intitul
    -0.07
     Заб
    -0.07
    (inplace
    -0.07
    -0.07
     bleaching
    -0.07
     agrade
    -0.07
    POSITIVE LOGITS
     UIText
    0.08
    -spe
    0.08
     Gos
    0.07
     daughters
    0.07
     facets
    0.07
    okuš
    0.07
     देता
    0.07
     edelleen
    0.07
     Daughter
    0.07
    તો
    0.07
    Activations Density 0.000%
    No Known Activations