Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 97114
    Prev
    Next
    INDEX
    Explanations

    international

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nationwide
    -0.09
     Counties
    -0.09
     Nationwide
    -0.08
     Skills
    -0.07
     জাতীয়
    -0.07
     Badge
    -0.07
     جان
    -0.07
     merveille
    -0.07
     yabo
    -0.07
     miy
    -0.07
    POSITIVE LOGITS
     forums
    0.16
     treaties
    0.16
     fora
    0.16
     agreements
    0.15
    论坛
    0.15
     accords
    0.15
     cooperation
    0.14
     tratados
    0.14
     organizations
    0.14
     Treat
    0.14
    Activations Density 0.028%

    No Known Activations