© 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. 18033
    Prev
    Next
    INDEX
    Explanations

    )=,=

    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
     колдон
    -0.08
    ైద
    -0.07
    ikten
    -0.07
     converting
    -0.07
     norske
    -0.07
     concierto
    -0.07
    สุด
    -0.07
    олога
    -0.07
     السود
    -0.07
    .experimental
    -0.07
    POSITIVE LOGITS
    ।↵↵
    0.09
    either
    0.09
    」。↵↵
    0.09
    ۔↵↵
    0.09
    pleasant
    0.09
    ±
    0.08
     ,↵↵
    0.08
     joko
    0.08
     .↵↵
    0.08
     ।↵↵
    0.08
    Activations Density 0.016%

    No Known Activations