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. 11772
    Prev
    Next
    INDEX
    Explanations

    geometric arrangements of spheres

    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
     sauv
    -0.09
     가지
    -0.08
    -0.08
     зы
    -0.08
    .എസ്
    -0.08
    ficiency
    -0.08
     확대
    -0.08
    跃
    -0.08
     کیږي
    -0.08
    ,key
    -0.08
    POSITIVE LOGITS
     walls
    0.10
    Walls
    0.09
     paredes
    0.09
     boundaries
    0.09
     confines
    0.09
     Walls
    0.08
     Obl
    0.07
     container
    0.07
     सीमा
    0.07
    лена
    0.07
    Activations Density 0.014%

    No Known Activations