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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109346
    Prev
    Next
    INDEX
    Explanations

    cleaning and safety

    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
     సంగీత
    -0.08
    ellipse
    -0.08
    迟
    -0.08
    /music
    -0.08
     서울
    -0.08
     exhibition
    -0.08
     음악
    -0.08
    /models
    -0.08
     vestidos
    -0.08
     malad
    -0.08
    POSITIVE LOGITS
     disinfect
    0.13
     chemicals
    0.12
     detergent
    0.12
     reagent
    0.12
     spraying
    0.12
     dosing
    0.12
     pesticide
    0.12
     deterg
    0.12
     biode
    0.12
     potency
    0.12
    Activations Density 0.029%

    No Known Activations