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. 112156
    Prev
    Next
    INDEX
    Explanations

    niño

    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
     הנש
    -0.08
     Asi
    -0.08
    ैर
    -0.07
     atlas
    -0.07
    -mo
    -0.07
    hoot
    -0.07
     للس
    -0.07
    িৰ
    -0.07
     Arth
    -0.07
    raf
    -0.07
    POSITIVE LOGITS
     climatic
    0.09
     climatique
    0.08
    cean
    0.08
    CX
    0.08
     próxim
    0.08
    BEC
    0.08
     climate
    0.08
     notoriously
    0.08
     episodes
    0.08
     фен
    0.08
    Activations Density 0.001%

    No Known Activations