© 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. 19-RESID-POST-AA
    11. 22890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    achdadh
    -0.09
     tegem
    -0.09
    ҳое
    -0.09
    ეების
    -0.09
     проведения
    -0.09
     jedh
    -0.09
     داشتن
    -0.08
    ირე
    -0.08
    ილების
    -0.08
    ħed
    -0.08
    POSITIVE LOGITS
    ically
    0.17
    적으로
    0.16
    ly
    0.16
    atively
    0.16
    istically
    0.16
    ily
    0.15
    lessly
    0.14
    -wise
    0.14
    ively
    0.14
    ously
    0.13
    Activations Density 0.094%

    No Known Activations