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. 53044
    Prev
    Next
    INDEX
    Explanations

    Wireless technology and health

    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
    ดี
    -0.08
     geweldige
    -0.07
     united
    -0.07
    精彩
    -0.07
    好的
    -0.07
     최고의
    -0.07
    ptious
    -0.07
     inform
    -0.07
     forbed
    -0.07
     ruthless
    -0.07
    POSITIVE LOGITS
     electromagnetic
    0.11
     elektrom
    0.10
    Corona
    0.09
     элект
    0.09
     энергет
    0.09
     GHz
    0.09
    atonin
    0.08
     қабыл
    0.08
     gradients
    0.08
     bloot
    0.08
    Activations Density 0.006%

    No Known Activations