© 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. 23-RESID-POST-AA
    11. 51955
    Prev
    Next
    INDEX
    Explanations

    Bon

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ות
    -0.08
     दल
    -0.08
     და
    -0.08
     Glad
    -0.08
     ги
    -0.08
     Outstanding
    -0.08
     Bg
    -0.08
     ụgwọ
    -0.08
     голуб
    -0.07
     envoyer
    -0.07
    POSITIVE LOGITS
    nes
    0.11
    ification
    0.10
    context
    0.10
    filename
    0.10
    panic
    0.09
    as
    0.09
    nych
    0.09
    um
    0.09
    adaptive
    0.09
    subset
    0.09
    Activations Density 0.000%

    No Known Activations