© 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. 71560
    Prev
    Next
    INDEX
    Explanations

    Code and language comparisons

    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
     DC
    -0.07
     Ber
    -0.07
     recovery
    -0.07
    -0.07
    .delete
    -0.07
     Chand
    -0.07
     Prob
    -0.07
     Deleted
    -0.07
     Monk
    -0.07
    -0.07
    POSITIVE LOGITS
     못
    0.09
    ISOString
    0.08
    _FIELDS
    0.08
    との差
    0.08
    (blank
    0.08
     termino
    0.08
     podremos
    0.08
    orera
    0.08
     accomod
    0.08
    (Item
    0.08
    Activations Density 0.000%
    No Known Activations