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. 120407
    Prev
    Next
    INDEX
    Explanations

    gym

    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
    ós
    -0.09
     mó
    -0.08
     সাধারণ
    -0.08
     অত্য
    -0.08
    -0.08
    Lastname
    -0.07
    LAS
    -0.07
     korzyst
    -0.07
     ব্যবহার
    -0.07
    -compatible
    -0.07
    POSITIVE LOGITS
     الكهربائية
    0.09
     ನಾಯಕ
    0.09
     sensores
    0.09
     നേത
    0.08
     Architectural
    0.08
     ಬಿಡುಗಡೆ
    0.08
     నాయక
    0.08
     vez
    0.08
     റില
    0.08
     territorial
    0.08
    Activations Density 0.001%

    No Known Activations