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. 43340
    Prev
    Next
    INDEX
    Explanations

    direct

    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
     incentives
    -0.09
     Zot
    -0.08
    Allocate
    -0.08
     Incent
    -0.08
     overtime
    -0.08
     allocation
    -0.08
    Bom
    -0.08
     nutritional
    -0.08
    	printk
    -0.08
    采购
    -0.08
    POSITIVE LOGITS
     окруж
    0.09
    ਿਰ
    0.08
     parab
    0.08
     Coul
    0.08
     દિવ
    0.08
     geometry
    0.08
     พระ
    0.08
    geschoss
    0.08
     भग
    0.08
     boundaries
    0.08
    Activations Density 0.007%

    No Known Activations