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. 75934
    Prev
    Next
    INDEX
    Explanations

    places

    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
    -called
    -0.08
     устро
    -0.08
    itum
    -0.08
     maioria
    -0.08
    程度
    -0.08
    -tier
    -0.08
    _TRACE
    -0.08
     plupart
    -0.08
     उसने
    -0.07
     sporten
    -0.07
    POSITIVE LOGITS
    ™
    0.11
    ®
    0.10
    Outlet
    0.09
    נן
    0.08
    ™,
    0.08
     IST
    0.08
    ના
    0.08
    bag
    0.07
     ®
    0.07
     Nie
    0.07
    Activations Density 0.189%

    No Known Activations