© 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. 26507
    Prev
    Next
    INDEX
    Explanations

    sushi

    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
     gritty
    -0.08
    )>>
    -0.08
     circumstances
    -0.07
     episod
    -0.07
     সংক
    -0.07
     candid
    -0.07
    _FP
    -0.07
    粗
    -0.07
     Athena
    -0.07
    429
    -0.07
    POSITIVE LOGITS
     sushi
    0.12
     Sushi
    0.12
    Pai
    0.08
    麻将
    0.08
     roulette
    0.08
    -slider
    0.08
    寿
    0.08
     csal
    0.08
     Specialist
    0.07
     uống
    0.07
    Activations Density 0.004%

    No Known Activations