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. 12088
    Prev
    Next
    INDEX
    Explanations

    check

    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
     determine
    -0.08
     entail
    -0.08
     neural
    -0.08
    IRONMENT
    -0.08
     implying
    -0.07
     airborne
    -0.07
     gep
    -0.07
     ખુશ
    -0.07
     binary
    -0.07
     HA
    -0.07
    POSITIVE LOGITS
    (wallet
    0.08
    पत्र
    0.08
    ूड
    0.08
     BX
    0.08
     Antonio
    0.08
     Baj
    0.08
    Antonio
    0.08
    Pete
    0.08
     nowhere
    0.08
     craftsmanship
    0.08
    Activations Density 0.004%

    No Known Activations