© 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. 17996
    Prev
    Next
    INDEX
    Explanations

    final

    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
    刷
    -0.08
    First
    -0.08
    	st
    -0.08
     doom
    -0.08
    	goto
    -0.08
    类
    -0.07
     bruges
    -0.07
    Do
    -0.07
    	io
    -0.07
    REP
    -0.07
    POSITIVE LOGITS
    -midi
    0.09
     adapté
    0.09
     Resultado
    0.09
    eterangan
    0.09
    -bel
    0.09
     Knowledge
    0.08
     Interpretation
    0.08
     поним
    0.08
     ვიცი
    0.08
     საჭირო
    0.08
    Activations Density 0.017%

    No Known Activations