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. 65273
    Prev
    Next
    INDEX
    Explanations

    College sports teams/states

    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
    なので
    -0.08
    粗
    -0.08
    pilot
    -0.08
     unemployed
    -0.08
     empower
    -0.07
     spaz
    -0.07
    ibbons
    -0.07
     baja
    -0.07
     unemployment
    -0.07
     pani
    -0.07
    POSITIVE LOGITS
    lef
    0.08
     varieties
    0.08
     blockbuster
    0.08
     violation
    0.08
     fierce
    0.08
     formidable
    0.08
     rivalry
    0.07
     rival
    0.07
     solver
    0.07
     variet
    0.07
    Activations Density 0.021%

    No Known Activations