© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30861
    Prev
    Next
    INDEX
    Explanations

    sports

    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
     따른
    -0.09
     मिलने
    -0.09
    Insensitive
    -0.08
    .jasper
    -0.08
     Editing
    -0.08
     ziekenhuis
    -0.08
     Krankenhaus
    -0.08
     Paragraph
    -0.08
    헌
    -0.08
     poe
    -0.07
    POSITIVE LOGITS
     realms
    0.08
    实力
    0.08
     prowess
    0.07
     realm
    0.07
     lately
    0.07
     talent
    0.07
     success
    0.07
     supremacy
    0.07
     dominance
    0.07
     supporters
    0.07
    Activations Density 0.036%

    No Known Activations