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. 15-RESID-POST-AA
    6. 19179
    Prev
    Next
    INDEX
    Explanations

    garnish

    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
     પોતાની
    -0.10
     advant
    -0.09
    Smarty
    -0.08
    Totals
    -0.08
     પોતાના
    -0.08
    地主
    -0.08
    ASIC
    -0.08
    総
    -0.08
     диз
    -0.08
     મોબ
    -0.08
    POSITIVE LOGITS
     garnish
    0.14
     limón
    0.10
     citrus
    0.10
     Lime
    0.10
     removable
    0.10
    水果
    0.10
     lime
    0.10
     decorative
    0.09
     Garn
    0.09
     rinse
    0.08
    Activations Density 0.008%

    No Known Activations