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. 12785
    Prev
    Next
    INDEX
    Explanations

    Line

    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
    ुरी
    -0.09
     intents
    -0.08
     Dominican
    -0.08
    ाले
    -0.07
     adjunct
    -0.07
    厨房
    -0.07
     '<?
    -0.07
     parmes
    -0.07
     ballroom
    -0.07
    司法
    -0.07
    POSITIVE LOGITS
    走势
    0.14
    走势图
    0.14
    _curve
    0.13
     plotted
    0.13
     curves
    0.12
     plotting
    0.11
     curve
    0.11
    Curve
    0.11
     الرسم
    0.11
    _plot
    0.11
    Activations Density 0.010%

    No Known Activations