© 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. 94846
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
     Hollywood
    -0.08
     quotes
    -0.08
     addresses
    -0.08
     hollywood
    -0.07
     procrast
    -0.07
     pirates
    -0.07
    'aéroport
    -0.07
     sorted
    -0.07
     hilarious
    -0.07
     βιβ
    -0.07
    POSITIVE LOGITS
     खाने
    0.09
    wayo
    0.09
    �
    0.09
     gamme
    0.09
     лечеб
    0.08
     खाना
    0.08
     Introdu
    0.08
    _ratio
    0.08
     菠菜
    0.08
    [max
    0.08
    Activations Density 0.012%

    No Known Activations