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. 106248
    Prev
    Next
    INDEX
    Explanations

    electromechanical systems

    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
    brook
    -0.08
     frères
    -0.08
     frère
    -0.08
    手機
    -0.08
    wil
    -0.07
     Conseil
    -0.07
     Citr
    -0.07
     Nieder
    -0.07
     East
    -0.07
     Bono
    -0.07
    POSITIVE LOGITS
    fect
    0.09
    530
    0.08
    ™
    0.08
     procéd
    0.07
     Rowling
    0.07
    'd
    0.07
    ример
    0.07
    ellaneous
    0.07
     ':
    0.07
    ам
    0.07
    Activations Density 0.052%

    No Known Activations