© 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. 95296
    Prev
    Next
    INDEX
    Explanations

    term

    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
     Chardonnay
    -0.09
     Urdu
    -0.08
    ibbon
    -0.07
    ږ
    -0.07
    יכה
    -0.07
    osaic
    -0.07
     ніж
    -0.07
    loquent
    -0.07
    ikult
    -0.07
     Burgundy
    -0.07
    POSITIVE LOGITS
     دين
    0.08
     courses
    0.08
     мошен
    0.08
    骗局
    0.07
     patrocin
    0.07
    attachments
    0.07
     recyclable
    0.07
     losers
    0.07
     MATERIAL
    0.07
     confession
    0.07
    Activations Density 0.002%

    No Known Activations