© 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. 19-RESID-POST-AA
    11. 103132
    Prev
    Next
    INDEX
    Explanations

    into

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Publishing
    -0.10
    Administr
    -0.09
    Use
    -0.09
    Semantic
    -0.09
    Gebruik
    -0.09
    Gaming
    -0.09
    </
    -0.09
    Implement
    -0.08
    随着
    -0.08
    ستخدم
    -0.08
    POSITIVE LOGITS
     equation
    0.16
     equations
    0.15
     the
    0.15
     expression
    0.14
     formula
    0.14
     formulas
    0.13
     expressions
    0.13
    :↵↵
    0.12
     our
    0.12
     those
    0.11
    Activations Density 0.005%

    No Known Activations