© 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. 3-RESID-POST-AA
    11. 1519
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _scope
    -0.08
    制度
    -0.08
    ก
    -0.07
     кол
    -0.07
     settlement
    -0.07
     сти
    -0.07
     cron
    -0.07
     താമ
    -0.07
     {:
    -0.07
     rightly
    -0.07
    POSITIVE LOGITS
     primul
    0.09
     Verk
    0.08
    mega
    0.08
     étape
    0.08
     Combat
    0.08
     Veronica
    0.08
     potato
    0.08
     Mb
    0.08
     Nt
    0.07
    .Tx
    0.07
    Activations Density 0.000%

    No Known Activations