© 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. 25218
    Prev
    Next
    INDEX
    Explanations

    file formats

    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
     lights
    -0.09
     fırs
    -0.09
     Antonio
    -0.09
     luces
    -0.08
     tratamientos
    -0.08
     Father's
    -0.08
     retrospect
    -0.08
     colleges
    -0.08
     Antony
    -0.08
    Departments
    -0.08
    POSITIVE LOGITS
    格式
    0.17
     formatos
    0.16
     formats
    0.16
     формат
    0.15
     Formats
    0.14
     формате
    0.14
     formaat
    0.14
    _formats
    0.13
     格
    0.13
    _format
    0.13
    Activations Density 0.042%

    No Known Activations