© 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. 44917
    Prev
    Next
    INDEX
    Explanations

    to

    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
    IBM
    -0.08
    Bon
    -0.08
    (visitor
    -0.08
    ினார்
    -0.08
    /inc
    -0.08
    Modification
    -0.08
    컬
    -0.08
    Cou
    -0.08
    [`
    -0.08
    (Log
    -0.08
    POSITIVE LOGITS
     diminishing
    0.09
     सुरक्षा
    0.08
     दश
    0.08
     తగ్గ
    0.08
     reducing
    0.08
     dí
    0.08
     порядок
    0.07
     diminish
    0.07
     Blood
    0.07
     ദിവസ
    0.07
    Activations Density 0.002%

    No Known Activations