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. 102900
    Prev
    Next
    INDEX
    Explanations

    evaluate

    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
    รา
    -0.08
     Artifact
    -0.08
     şey
    -0.08
     parent's
    -0.08
     auxqu
    -0.07
     чему
    -0.07
     thì
    -0.07
     sevent
    -0.07
     macam
    -0.07
     순
    -0.07
    POSITIVE LOGITS
     regularmente
    0.11
     régulièrement
    0.10
     annually
    0.09
     regelmäßig
    0.09
     periodically
    0.09
     crossroads
    0.08
     regularly
    0.08
    每日
    0.08
     consulted
    0.08
     routinely
    0.08
    Activations Density 0.011%

    No Known Activations