© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65381
    Prev
    Next
    INDEX
    Explanations

    requirements

    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
     goût
    -0.10
     чиг
    -0.08
     Crus
    -0.08
     soutien
    -0.07
     вкус
    -0.07
     icy
    -0.07
     teal
    -0.07
     narrowing
    -0.07
    -burning
    -0.07
     unmistak
    -0.07
    POSITIVE LOGITS
    无需
    0.12
    -ақ
    0.10
    済
    0.09
    不用
    0.09
     relying
    0.09
    ாமல்
    0.09
    即可
    0.08
     sparen
    0.08
     relies
    0.08
    ,只
    0.08
    Activations Density 0.091%

    No Known Activations