© 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. 23-RESID-POST-AA
    11. 52250
    Prev
    Next
    INDEX
    Explanations

    martial arts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _plural
    -0.09
     Hers
    -0.08
    ாட்ச
    -0.08
    買
    -0.08
    ாட்சி
    -0.08
    Indexer
    -0.08
    _candidates
    -0.07
    加工
    -0.07
    _album
    -0.07
    出演
    -0.07
    POSITIVE LOGITS
     муай
    0.18
     karate
    0.18
     kung
    0.17
     Karate
    0.17
     кун
    0.16
     aiki
    0.15
     Kung
    0.15
     martial
    0.15
    Kung
    0.14
     kata
    0.13
    Activations Density 0.025%

    No Known Activations