© 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. 71257
    Prev
    Next
    INDEX
    Explanations

    in

    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
     предоставляет
    -0.09
    க்கம்
    -0.09
     दोष
    -0.09
     proporciona
    -0.09
    着
    -0.08
     محت
    -0.08
     proceedings
    -0.08
    дад
    -0.08
    بيب
    -0.08
    ّل
    -0.08
    POSITIVE LOGITS
     Tier
    0.09
     defender
    0.08
     tier
    0.08
     stacked
    0.08
     barric
    0.08
    '.
    0.07
    Pinned
    0.07
    /O
    0.07
    Tier
    0.07
    .o
    0.07
    Activations Density 0.003%

    No Known Activations