© 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. 110025
    Prev
    Next
    INDEX
    Explanations

    platform

    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
    irc
    -0.08
    ーティ
    -0.08
    ébergement
    -0.07
    人生
    -0.07
    _UPDATED
    -0.07
    bern
    -0.07
    ropped
    -0.07
    omorphic
    -0.07
    Initialized
    -0.07
     garota
    -0.07
    POSITIVE LOGITS
     heath
    0.09
    长度
    0.09
     accueill
    0.08
     seconds
    0.08
    Entrance
    0.08
     kilometers
    0.08
     kilometer
    0.08
     مدة
    0.08
     препят
    0.08
    _width
    0.08
    Activations Density 0.010%

    No Known Activations