© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1008
    Prev
    Next
    INDEX
    Explanations

    omp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fastest
    -0.07
     nap
    -0.07
    Iterable
    -0.07
    table
    -0.07
     zest
    -0.07
    ssd
    -0.07
    =");↵
    -0.07
    Largest
    -0.07
    ाहर
    -0.07
     Büyük
    -0.07
    POSITIVE LOGITS
     kwuru
    0.08
    (Core
    0.08
     ị
    0.08
     devolución
    0.08
     masonry
    0.08
    леб
    0.08
     pagtat
    0.08
     بدأ
    0.08
     дик
    0.08
     yakho
    0.08
    Activations Density 0.001%

    No Known Activations