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. 53867
    Prev
    Next
    INDEX
    Explanations

    pepper

    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
     afast
    -0.08
     maw
    -0.07
    逐
    -0.07
    .soap
    -0.07
     avoided
    -0.07
     satin
    -0.07
     rung
    -0.07
     furl
    -0.07
    йш
    -0.07
    ப்படி
    -0.07
    POSITIVE LOGITS
     synerg
    0.12
     enhancing
    0.10
     accompanying
    0.10
     synergy
    0.10
     compañero
    0.09
     potenciar
    0.09
     enhances
    0.09
     enhance
    0.09
     Enhance
    0.09
     contexto
    0.09
    Activations Density 0.010%

    No Known Activations