© 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. 129408
    Prev
    Next
    INDEX
    Explanations

    Numbers and amounts

    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
    Secretary
    -0.09
    /eclipse
    -0.09
     whistle
    -0.09
     secretary
    -0.08
     Plateau
    -0.08
     alfabet
    -0.08
     pleg
    -0.08
     warriors
    -0.08
    -paced
    -0.08
    Pir
    -0.08
    POSITIVE LOGITS
     रकम
    0.10
     liabilities
    0.09
    金额
    0.09
    ^^^^^^^^
    0.09
     discrepancies
    0.08
     объем
    0.08
     спис
    0.08
     مبلغ
    0.07
     sizeable
    0.07
     көлем
    0.07
    Activations Density 0.020%

    No Known Activations