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. 120057
    Prev
    Next
    INDEX
    Explanations

    translate

    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
     توسعه
    -0.08
     Cylinder
    -0.08
    Οι
    -0.08
     Hanson
    -0.08
     consta
    -0.07
     Hans
    -0.07
     chlorine
    -0.07
     megap
    -0.07
    STE
    -0.07
     radion
    -0.07
    POSITIVE LOGITS
     pequenos
    0.08
    /html
    0.08
     કરી
    0.08
    事項
    0.08
    ila
    0.08
    ley
    0.08
    含
    0.07
     যায়
    0.07
    úe
    0.07
    雅黑
    0.07
    Activations Density 0.007%

    No Known Activations