© 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. 65485
    Prev
    Next
    INDEX
    Explanations

    absurdity and humor

    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
     νε
    -0.09
     суще
    -0.08
     сформ
    -0.08
    .Н
    -0.08
    kani
    -0.08
     പല
    -0.08
    ,we
    -0.08
     данной
    -0.08
    .Т
    -0.08
     формирования
    -0.08
    POSITIVE LOGITS
     hilarious
    0.15
     bizarre
    0.15
     😂
    0.14
     absurd
    0.14
     ridiculously
    0.14
     antics
    0.13
     quirky
    0.13
     amusing
    0.13
     jokes
    0.12
     ridiculous
    0.12
    Activations Density 1.350%

    No Known Activations