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. 119243
    Prev
    Next
    INDEX
    Explanations

    code

    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
     beings
    -0.08
     insolv
    -0.08
     Nations
    -0.08
     nations
    -0.08
     pretend
    -0.08
     tlang
    -0.07
     tegn
    -0.07
     tswa
    -0.07
     hereby
    -0.07
     kamata
    -0.07
    POSITIVE LOGITS
    schild
    0.09
     grille
    0.08
     пред
    0.07
     мак
    0.07
    وق
    0.07
     выс
    0.07
     представлен
    0.07
    oa
    0.07
     coil
    0.07
    aine
    0.07
    Activations Density 0.000%

    No Known Activations