© 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. 29104
    Prev
    Next
    INDEX
    Explanations

    Space/stars

    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
    ogy
    -0.08
     defeated
    -0.08
     riêng
    -0.08
    -suite
    -0.07
    амер
    -0.07
     CSU
    -0.07
     הגד
    -0.07
    ുത
    -0.07
    semester
    -0.07
     historischen
    -0.07
    POSITIVE LOGITS
    _minutes
    0.08
    Modificar
    0.08
    passing
    0.08
     symbols
    0.08
     circles
    0.08
    Mostrar
    0.08
    symbols
    0.08
    Pinterest
    0.08
    oplastic
    0.08
     Código
    0.07
    Activations Density 0.001%

    No Known Activations