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

    Neuronpedia

    APICircuit 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. 75960
    Prev
    Next
    INDEX
    Explanations

    Watermark

    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
    zipcode
    -0.09
    続きを
    -0.08
     Kos
    -0.08
    atorias
    -0.08
     postcode
    -0.08
     recue
    -0.08
     carros
    -0.08
     കഴിയ
    -0.07
     zipcode
    -0.07
     reunited
    -0.07
    POSITIVE LOGITS
     watermark
    0.09
    图片
    0.09
     ছব
    0.09
    照片
    0.08
     пиш
    0.08
     ছবি
    0.07
    Aircraft
    0.07
    ថ
    0.07
    /logo
    0.07
    Automatically
    0.07
    Activations Density 0.002%

    No Known Activations