© 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. 109875
    Prev
    Next
    INDEX
    Explanations

    greek letters

    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
    hon
    -0.08
    eregister
    -0.08
    —including
    -0.08
    Hon
    -0.08
     эф
    -0.08
    ares
    -0.08
     дорог
    -0.07
    [color
    -0.07
     Hon
    -0.07
    -network
    -0.07
    POSITIVE LOGITS
     weighting
    0.09
     Gewicht
    0.08
     alam
    0.08
     ഭാര
    0.08
     empirical
    0.08
     وزن
    0.08
     balancing
    0.08
     ಕಾಂ
    0.07
     weighing
    0.07
    _WEIGHT
    0.07
    Activations Density 0.014%

    No Known Activations