© 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. 30984
    Prev
    Next
    INDEX
    Explanations

    go

    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
     निर्म
    -0.08
    075
    -0.08
     kp
    -0.08
     शुरुआत
    -0.07
     adjoining
    -0.07
     introductions
    -0.07
    507
    -0.07
     inic
    -0.07
    emit
    -0.07
    qp
    -0.07
    POSITIVE LOGITS
     ponen
    0.08
     parar
    0.08
     Cruz
    0.08
     처리
    0.08
     Zusamm
    0.08
    naar
    0.08
     діт
    0.07
    bels
    0.07
     Dicken
    0.07
     դեպի
    0.07
    Activations Density 0.044%

    No Known Activations