Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 113958
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
     IO
    -0.08
     recommended
    -0.08
    recommended
    -0.08
     Extension
    -0.08
     Explorer
    -0.08
     महान
    -0.08
     extension
    -0.08
     концер
    -0.07
     प्रदर्शन
    -0.07
     Metro
    -0.07
    POSITIVE LOGITS
    _after
    0.09
    .after
    0.09
     akhir
    0.08
    After
    0.08
    (after
    0.08
     olmuş
    0.08
    Alex
    0.08
    "But
    0.08
    Reported
    0.08
    larından
    0.08
    Activations Density 0.057%

    No Known Activations