© 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. 17905
    Prev
    Next
    INDEX
    Explanations

    replacement

    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
     другие
    -0.08
     иногда
    -0.08
     некоторые
    -0.08
     способы
    -0.08
     другое
    -0.08
     похож
    -0.07
     некоторых
    -0.07
     joskus
    -0.07
    chmal
    -0.07
    Another
    -0.07
    POSITIVE LOGITS
     presumably
    0.31
     vermutlich
    0.28
     provavelmente
    0.27
     waarschijnlijk
    0.27
     probablemente
    0.26
     wahrscheinlich
    0.26
     probably
    0.26
     probablement
    0.26
     likely
    0.25
    probably
    0.23
    Activations Density 0.342%

    No Known Activations