© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71728
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
    Negative Logits
     peroxide
    -0.08
     Weiss
    -0.08
    брь
    -0.08
    ។↵
    -0.08
     català
    -0.08
    年来
    -0.08
     Crab
    -0.08
     Sikh
    -0.08
     Zijn
    -0.08
    ательная
    -0.08
    POSITIVE LOGITS
    000
    0.08
    00
    0.08
    123
    0.08
    @example
    0.08
    .matcher
    0.08
    789
    0.07
    076
    0.07
    .cloudflare
    0.07
     fabricate
    0.07
    130
    0.07
    Activations Density 0.003%

    No Known Activations