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. 88282
    Prev
    Next
    INDEX
    Explanations

    grazing

    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
    Aside
    -0.08
    _NOT
    -0.07
    Measure
    -0.07
    lem
    -0.07
    sx
    -0.07
    096
    -0.07
     vän
    -0.07
    138
    -0.07
     centrifugal
    -0.07
     prove
    -0.07
    POSITIVE LOGITS
     inplace
    0.08
     pr
    0.08
     пр
    0.08
    面积
    0.08
     rocky
    0.08
     Zell
    0.08
     ప్ర
    0.08
    етки
    0.07
     contribu
    0.07
    ారణ
    0.07
    Activations Density 0.003%

    No Known Activations