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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91396
    Prev
    Next
    INDEX
    Explanations

    grid graphs

    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
    -from
    -0.08
     رسول
    -0.08
    -0.08
     feminine
    -0.07
    (callback
    -0.07
     depuis
    -0.07
     чтобы
    -0.07
    Mond
    -0.07
     caller
    -0.07
    Bride
    -0.07
    POSITIVE LOGITS
     Accounting
    0.09
    -sem
    0.08
    ison
    0.08
     Structure
    0.08
     Coordination
    0.08
     adhesive
    0.08
     Semaphore
    0.08
     slab
    0.08
     Navigation
    0.08
     Inclusion
    0.07
    Activations Density 0.033%
    No Known Activations