© 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. 110192
    Prev
    Next
    INDEX
    Explanations

    or

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Semaphore
    -0.08
    еин
    -0.07
    Walker
    -0.07
    Unlocked
    -0.07
     Schon
    -0.07
     Vikt
    -0.07
    -0.07
     reclaimed
    -0.07
     säh
    -0.07
    _Service
    -0.07
    POSITIVE LOGITS
    ้อมูล
    0.09
    Xi
    0.09
     elaborado
    0.09
     paragraphs
    0.08
     Xi
    0.08
    様
    0.07
     elaborar
    0.07
     зг
    0.07
     elaboración
    0.07
     REP
    0.07
    Activations Density 0.003%
    No Known Activations