© 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 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. 63781
    Prev
    Next
    INDEX
    Explanations

    3

    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
     occasione
    -0.07
    侯
    -0.07
     corrig
    -0.07
     tone
    -0.07
     sociedades
    -0.07
    'ind
    -0.07
    _collect
    -0.07
     Elizabeth
    -0.07
     Romance
    -0.07
     title
    -0.07
    POSITIVE LOGITS
     STAFF
    0.09
     ringan
    0.08
    0.08
     سرعت
    0.08
     curly
    0.08
     ligero
    0.07
    өөл
    0.07
    صفات
    0.07
    anie
    0.07
     불
    0.07
    Activations Density 0.021%
    No Known Activations