© 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. 71448
    Prev
    Next
    INDEX
    Explanations

    volatile

    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
     gant
    -0.09
    ders
    -0.08
    izma
    -0.08
    sev
    -0.08
    Disabled
    -0.08
    рев
    -0.08
     devotion
    -0.08
     beating
    -0.07
    vival
    -0.07
     slow
    -0.07
    POSITIVE LOGITS
    volatile
    0.09
     والمت
    0.08
     volatile
    0.08
     Ein
    0.08
     termed
    0.08
     carbohydrates
    0.08
     regulatory
    0.08
     substances
    0.08
     assunto
    0.08
     вещества
    0.08
    Activations Density 0.002%

    No Known Activations