© 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. 129129
    Prev
    Next
    INDEX
    Explanations

    Alt

    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
     ranged
    -0.09
    025
    -0.08
    ursal
    -0.08
     conducción
    -0.08
     RANGE
    -0.08
    CRUD
    -0.07
     stages
    -0.07
    Range
    -0.07
    /preferences
    -0.07
    UILD
    -0.07
    POSITIVE LOGITS
    _j
    0.08
     jól
    0.08
    burn
    0.08
     картинки
    0.08
    tuple
    0.07
    urb
    0.07
     folha
    0.07
     overthrow
    0.07
    ungeons
    0.07
     Shutdown
    0.07
    Activations Density 0.002%

    No Known Activations