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. 11639
    Prev
    Next
    INDEX
    Explanations

    matplotlib

    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
    ე
    -0.08
     Wort
    -0.07
    852
    -0.07
    贸
    -0.07
     outright
    -0.07
     matéri
    -0.07
    絶
    -0.07
     workmanship
    -0.07
     deliber
    -0.07
     Belle
    -0.07
    POSITIVE LOGITS
    .pyplot
    0.13
    .imshow
    0.11
    imshow
    0.09
     pyplot
    0.09
    .plot
    0.09
    .savefig
    0.08
    Sci
    0.08
    .jfree
    0.08
    mpl
    0.08
     сосуд
    0.08
    Activations Density 0.002%

    No Known Activations