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. 58429
    Prev
    Next
    INDEX
    Explanations

    Chemical dissolution

    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
     zero
    -0.08
     प्रेम
    -0.08
     Static
    -0.08
    Static
    -0.08
     HTML
    -0.07
     पह
    -0.07
     buttons
    -0.07
     кнопку
    -0.07
    धा
    -0.07
     встанов
    -0.07
    POSITIVE LOGITS
     soluble
    0.13
     dissolve
    0.12
     раствор
    0.12
     dissolved
    0.11
     dissolution
    0.11
     disper
    0.10
     dissol
    0.10
     раств
    0.09
     breakup
    0.09
     liquor
    0.09
    Activations Density 0.011%

    No Known Activations