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. 15-RESID-POST-AA
    6. 19422
    Prev
    Next
    INDEX
    Explanations

    medieval context

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESPN
    -0.11
     NCAA
    -0.11
    美国
    -0.11
     美国
    -0.11
     headphone
    -0.11
     Oprah
    -0.10
    firebase
    -0.10
    ,美国
    -0.10
     ADHD
    -0.10
     американ
    -0.10
    POSITIVE LOGITS
     nobles
    0.15
     guild
    0.14
     apprentice
    0.13
    Faction
    0.13
     राजा
    0.13
     villagers
    0.13
    Guild
    0.13
     armor
    0.12
     गाँव
    0.12
     medieval
    0.12
    Activations Density 0.125%

    No Known Activations