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. 113035
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     هوا
    -0.08
    。例如
    -0.08
    (OP
    -0.07
    cine
    -0.07
     ساعات
    -0.07
    Https
    -0.07
    [arg
    -0.07
     neben
    -0.07
     LS
    -0.07
    。其中
    -0.07
    POSITIVE LOGITS
    0.08
     ấy
    0.08
     booda
    0.08
     ix
    0.08
     પાછ
    0.08
    之后
    0.08
    以后
    0.07
     subsequent
    0.07
     onwards
    0.07
     onward
    0.07
    Activations Density 0.065%

    No Known Activations