© 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. 8061
    Prev
    Next
    INDEX
    Explanations

    1

    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
    724
    -0.11
    多少
    -0.08
    Caught
    -0.08
    Yoga
    -0.08
    Zones
    -0.08
    Zona
    -0.08
     Zona
    -0.07
     Wider
    -0.07
     calculators
    -0.07
    /blog
    -0.07
    POSITIVE LOGITS
     importantly
    0.09
    事項
    0.09
    _constraints
    0.09
     соблю
    0.09
     constraints
    0.09
     Constraint
    0.08
    Constraints
    0.08
    constraints
    0.08
     사항
    0.08
     Constraints
    0.08
    Activations Density 0.037%

    No Known Activations