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. 15-RESID-POST-AA
    6. 18955
    Prev
    Next
    INDEX
    Explanations

    collar

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MATLAB
    -0.08
    itaa
    -0.07
     directive
    -0.07
     Classical
    -0.07
     SHA
    -0.07
     ganze
    -0.07
     MD
    -0.07
     gaussian
    -0.07
     entire
    -0.07
     statistical
    -0.07
    POSITIVE LOGITS
     צבע
    0.11
     تحتوي
    0.10
     branded
    0.09
    -coated
    0.09
    badge
    0.09
     يحتوي
    0.09
     reflecting
    0.09
     headed
    0.09
     متنوعة
    0.09
    	color
    0.09
    Activations Density 0.003%

    No Known Activations