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. 15-RESID-POST-AA
    6. 64
    Prev
    Next
    INDEX
    Explanations

    }}

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    -0.11
    o
    -0.10
     fishing
    -0.09
    e
    -0.09
     in
    -0.08
    (types
    -0.08
    -related
    -0.08
    -level
    -0.08
     demographics
    -0.08
    (update
    -0.08
    POSITIVE LOGITS
     Gwyn
    0.08
     Alemanha
    0.08
     Germans
    0.08
     Bulg
    0.08
     realizadas
    0.08
     alemán
    0.08
     desn
    0.08
    	Json
    0.08
     airplanes
    0.08
     suh
    0.08
    Activations Density 0.003%

    No Known Activations