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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47937
    Prev
    Next
    INDEX
    Explanations

    trade

    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
    .archive
    -0.10
    .timestamp
    -0.09
     legality
    -0.09
    _author
    -0.09
     legales
    -0.09
     x
    -0.09
     legais
    -0.08
    _timestamp
    -0.08
     timestamp
    -0.08
     AUTHOR
    -0.08
    POSITIVE LOGITS
     tradem
    0.19
     trade
    0.18
     Trade
    0.18
    Trade
    0.17
    trade
    0.16
     ट्रेड
    0.16
    _trade
    0.15
     know
    0.14
    .trade
    0.13
     traded
    0.13
    Activations Density 0.014%

    No Known Activations