© 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. 11-RESID-POST-AA
    11. 78155
    Prev
    Next
    INDEX
    Explanations

    555

    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
     jelent
    -0.08
     proportions
    -0.08
     shelf
    -0.08
     Jar
    -0.07
     seguida
    -0.07
    Jar
    -0.07
    ybės
    -0.07
    ieli
    -0.07
    memor
    -0.07
    謝
    -0.07
    POSITIVE LOGITS
     золот
    0.08
    ্
    0.08
    ्घ
    0.08
    েড
    0.08
    াকা
    0.08
     berk
    0.08
     صن
    0.08
    коў
    0.08
     винов
    0.08
     hypot
    0.07
    Activations Density 0.002%

    No Known Activations