© 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. 11-RESID-POST-AA
    11. 71746
    Prev
    Next
    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    /cm
    -0.08
    /table
    -0.08
    /cr
    -0.08
    /data
    -0.07
    /T
    -0.07
    nelly
    -0.07
    maybe
    -0.07
     Jam
    -0.07
    median
    -0.07
     apologise
    -0.07
    POSITIVE LOGITS
     Clearly
    0.09
     явно
    0.09
    ьер
    0.09
     <<↵
    0.08
     URL
    0.08
     मंत्रालय
    0.08
     acessórios
    0.08
    アクセ
    0.08
     Bakan
    0.08
     дах
    0.08
    Activations Density 0.063%

    No Known Activations