© 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. 23-RESID-POST-AA
    11. 97858
    Prev
    Next
    INDEX
    Explanations

    say forward or backward slashes and/or parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -ste
    -0.09
     gereden
    -0.09
    ’air
    -0.09
    кер
    -0.09
    必中
    -0.09
    тереү
    -0.09
    -日本
    -0.09
     სრული
    -0.09
    -awareness
    -0.09
    იკის
    -0.09
    POSITIVE LOGITS
    }{
    0.10
     an
    0.08
     એક
    0.08
    )((
    0.07
     Technology
    0.07
     one
    0.07
     alg
    0.07
     oly
    0.07
     ((
    0.07
    )(_
    0.07
    Activations Density 0.063%

    No Known Activations