© 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. 109931
    Prev
    Next
    INDEX
    Explanations

    sure certain

    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
    adx
    -0.08
     intuitive
    -0.08
    success
    -0.08
    heta
    -0.08
    ady
    -0.08
    prior
    -0.07
    .idx
    -0.07
    impl
    -0.07
    solve
    -0.07
     직
    -0.07
    POSITIVE LOGITS
     ciert
    0.08
     peliculas
    0.08
     πως
    0.08
    Pues
    0.08
     fatto
    0.08
     cenas
    0.08
     oe
    0.07
     Company's
    0.07
     caf
    0.07
    رو
    0.07
    Activations Density 0.009%

    No Known Activations