© 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. 17992
    Prev
    Next
    INDEX
    Explanations

    modern

    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
     médecins
    -0.09
    	login
    -0.09
     surgeon
    -0.09
    -0.09
     dentists
    -0.09
    /login
    -0.08
    =mysql
    -0.08
     poet
    -0.08
     bactér
    -0.08
     (__
    -0.08
    POSITIVE LOGITS
     modern
    0.13
     digital
    0.12
     современной
    0.12
     цифров
    0.12
     현대
    0.11
     modernen
    0.11
    现代
    0.11
     डिजिटल
    0.10
     دیج
    0.10
     today's
    0.10
    Activations Density 0.071%

    No Known Activations