© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94391
    Prev
    Next
    INDEX
    Explanations

    economics and rational decisions

    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
    GPIO
    -0.08
     Guitar
    -0.08
    Scroll
    -0.08
     MIDI
    -0.08
     ceremonial
    -0.08
     cym
    -0.08
     scroll
    -0.08
     Kabel
    -0.08
    -0.08
    -0.08
    POSITIVE LOGITS
     prices
    0.10
     рын
    0.10
     markets
    0.10
    prices
    0.09
    Prices
    0.09
    _prices
    0.09
     Prices
    0.09
     Markets
    0.09
     beliefs
    0.09
     incomes
    0.09
    Activations Density 0.006%
    No Known Activations