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. 23-RESID-POST-AA
    6. 98286
    Prev
    Next
    INDEX
    Explanations

    Requesting confirmation, French

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     заверш
    -0.10
     completion
    -0.10
    Completion
    -0.09
     പൂ
    -0.08
    _completion
    -0.08
     amplitude
    -0.08
    'p
    -0.08
    (sprintf
    -0.08
    _COMPLE
    -0.08
    .Sprintf
    -0.08
    POSITIVE LOGITS
     accus
    0.12
     acc
    0.09
     Acc
    0.09
     considér
    0.08
    _acc
    0.08
     tiens
    0.08
     bien
    0.08
    acc
    0.08
    .acc
    0.08
    Acc
    0.08
    Activations Density 0.001%

    No Known Activations