© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77963
    Prev
    Next
    INDEX
    Explanations

    ief

    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
     literacy
    -0.09
    ેક્ટ
    -0.08
    habit
    -0.08
     연락
    -0.08
     contactar
    -0.08
     postcode
    -0.08
     visitas
    -0.08
     Coach
    -0.07
     outreach
    -0.07
     reuniones
    -0.07
    POSITIVE LOGITS
    IMM
    0.10
    _button
    0.08
     hlub
    0.08
     BUTTON
    0.08
    ulum
    0.08
     beve
    0.08
     raised
    0.08
    daki
    0.08
     difficult
    0.08
     deeper
    0.07
    Activations Density 0.001%

    No Known Activations