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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6151
    Prev
    Next
    INDEX
    Explanations

    Period

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "?
    -0.09
     confusion
    -0.09
     wondering
    -0.09
    20
    -0.09
     wondered
    -0.09
     simpele
    -0.08
    2
    -0.08
     confusing
    -0.08
     wonder
    -0.08
    which
    -0.08
    POSITIVE LOGITS
     Write
    0.15
     Instructions
    0.15
     Requirements
    0.14
     Additional
    0.14
     Ensure
    0.13
     Additionally
    0.13
     Analyze
    0.13
     Requirement
    0.12
     Instruction
    0.12
    Instructions
    0.12
    Activations Density 0.056%

    No Known Activations