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. 112896
    Prev
    Next
    INDEX
    Explanations

    Russian nesting dolls/Russia

    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
    炎
    -0.09
    (column
    -0.08
    青
    -0.08
    Contributor
    -0.08
    elift
    -0.08
     column
    -0.08
     columna
    -0.08
    (columns
    -0.08
     colonne
    -0.07
     سائ
    -0.07
    POSITIVE LOGITS
     nested
    0.17
     Nested
    0.17
    _nested
    0.17
    Nested
    0.17
    nested
    0.16
     nests
    0.14
     dolls
    0.13
     nesting
    0.12
     Nest
    0.12
     nest
    0.12
    Activations Density 0.008%

    No Known Activations