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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70510
    Prev
    Next
    INDEX
    Explanations

    Russian prepositions

    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
    hips
    -0.07
     Great
    -0.07
    -0.07
    ide
    -0.07
    tona
    -0.07
    hip
    -0.07
    [h
    -0.07
    hed
    -0.07
     Lac
    -0.07
    서는
    -0.07
    POSITIVE LOGITS
    全面
    0.07
    ാഗ
    0.07
     заб
    0.07
     работе
    0.07
     disclosure
    0.07
     NU
    0.07
     метал
    0.07
     ammonia
    0.07
    ിങ്ക
    0.07
     confession
    0.07
    Activations Density 0.002%
    No Known Activations