Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111886
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions

    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
     sombr
    -0.08
    меч
    -0.08
    ビ
    -0.08
    kie
    -0.08
    netje
    -0.08
     autorizado
    -0.08
     kabinet
    -0.08
     hoja
    -0.08
     чтобы
    -0.07
    angka
    -0.07
    POSITIVE LOGITS
    ZX
    0.08
    (Q
    0.08
    Backward
    0.07
     spelen
    0.07
     backwards
    0.07
    ))/
    0.07
    _Q
    0.07
    _CH
    0.07
    ,q
    0.07
    _iterations
    0.07
    Activations Density 0.090%

    No Known Activations