© 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. 18062
    Prev
    Next
    INDEX
    Explanations

    Electrical circuits

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     хэмжээ
    -0.10
     հատկ
    -0.09
     variedades
    -0.09
     սահման
    -0.09
     мөл
    -0.09
    <|reserved_200015|>
    -0.09
     hues
    -0.09
     Notices
    -0.09
     ʻano
    -0.09
     սեփական
    -0.09
    POSITIVE LOGITS
    连接
    0.15
     connected
    0.14
    -connected
    0.14
     જોડ
    0.13
     downstream
    0.13
     circuit
    0.13
     연결
    0.13
     இண
    0.13
    connected
    0.13
     bypass
    0.13
    Activations Density 0.020%

    No Known Activations