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. 43204
    Prev
    Next
    INDEX
    Explanations

    equations

    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
     thrive
    -0.08
     miss
    -0.08
     Carnival
    -0.08
     circumvent
    -0.07
     asylum
    -0.07
     hohe
    -0.07
     Hitch
    -0.07
     clogged
    -0.07
     cuyo
    -0.07
     RAD
    -0.07
    POSITIVE LOGITS
     birlikte
    0.08
     deduct
    0.07
    ஒ
    0.07
    �
    0.07
    லாம்
    0.07
    டு
    0.07
     vê
    0.07
     মতে
    0.07
    itam
    0.07
    cheng
    0.07
    Activations Density 0.013%

    No Known Activations