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. 43221
    Prev
    Next
    INDEX
    Explanations

    code

    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
    峰
    -0.09
    graduates
    -0.08
    .MESSAGE
    -0.08
     gratuite
    -0.07
    RAW
    -0.07
    MO
    -0.07
    োৱা
    -0.07
    ഷ
    -0.07
    농
    -0.07
     pathogen
    -0.07
    POSITIVE LOGITS
     eax
    0.09
     يخ
    0.08
     asm
    0.07
     وارد
    0.07
     elegance
    0.07
    ával
    0.07
     Tony
    0.07
     cref
    0.07
     innocence
    0.07
    μαν
    0.07
    Activations Density 0.001%

    No Known Activations