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. 113005
    Prev
    Next
    INDEX
    Explanations

    mix

    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
     eccles
    -0.09
     turpis
    -0.08
     धार्मिक
    -0.08
    rological
    -0.08
     theological
    -0.08
     bishop
    -0.08
    ifficulty
    -0.08
     religious
    -0.08
    ხედ
    -0.08
    oad
    -0.08
    POSITIVE LOGITS
     precipitation
    0.09
     precip
    0.09
    染
    0.08
     Raise
    0.08
     dye
    0.08
     latex
    0.08
     coag
    0.08
     বস
    0.08
    jsonp
    0.08
     staining
    0.07
    Activations Density 0.010%

    No Known Activations