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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 61177
    Prev
    Next
    INDEX
    Explanations

    Cutting edge

    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
     tucked
    -0.08
     Cricket
    -0.08
     touchdowns
    -0.07
    ాక్ష
    -0.07
    /actions
    -0.07
    Historia
    -0.07
     있었
    -0.07
     выг
    -0.07
     Tales
    -0.07
     concernés
    -0.07
    POSITIVE LOGITS
     technology
    0.11
     tecnolog
    0.10
     Technologie
    0.10
    તમ
    0.10
     technologie
    0.10
     ביותר
    0.10
    technology
    0.10
    先进
    0.09
     tecnologia
    0.09
     tecnológica
    0.09
    Activations Density 0.035%

    No Known Activations