© 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. 19-RESID-POST-AA
    11. 102819
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    if
    -0.10
     dengan
    -0.09
    oc
    -0.09
    571
    -0.09
     untuk
    -0.08
    studio
    -0.08
    061
    -0.08
    ches
    -0.08
    liq
    -0.08
    clinical
    -0.08
    POSITIVE LOGITS
     decomposition
    0.11
    лении
    0.11
     составе
    0.11
     numerator
    0.11
     σε
    0.10
     розвитку
    0.10
     προϊόν
    0.10
     einhver
    0.10
     expression
    0.10
     Produkten
    0.10
    Activations Density 0.020%

    No Known Activations