© 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. 95183
    Prev
    Next
    INDEX
    Explanations

    Comparisons and intensifications

    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
    so
    -0.07
    Executive
    -0.07
    azh
    -0.07
    asuk
    -0.07
     Cano
    -0.07
    Slip
    -0.07
     executive
    -0.07
     Shen
    -0.07
    olin
    -0.07
    LEGE
    -0.07
    POSITIVE LOGITS
     nonexistent
    0.08
     estará
    0.07
     accordingly
    0.07
     QColor
    0.07
     hơn
    0.07
     eftersom
    0.07
    since
    0.07
     parent's
    0.07
    ость
    0.07
     living
    0.07
    Activations Density 0.182%

    No Known Activations