Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43839
    Prev
    Next
    INDEX
    Explanations

    Logarithms

    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
    agog
    -0.08
     Heb
    -0.08
     వ్యవ
    -0.07
     eas
    -0.07
     жа
    -0.07
     alumin
    -0.07
     modality
    -0.07
     sting
    -0.07
     пов
    -0.07
    rope
    -0.07
    POSITIVE LOGITS
     abr
    0.08
    stoff
    0.08
    enk
    0.08
     Wart
    0.07
     Deputy
    0.07
    ON
    0.07
    iously
    0.07
     Cu
    0.07
     시행
    0.07
    ну
    0.07
    Activations Density 0.129%

    No Known Activations