© 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. 11-RESID-POST-AA
    11. 95370
    Prev
    Next
    INDEX
    Explanations

    trading

    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
     perl
    -0.08
     inco
    -0.08
    Circ
    -0.07
     Som
    -0.07
    robat
    -0.07
     hukum
    -0.07
    Tray
    -0.07
     Gesellschaft
    -0.07
     Mek
    -0.07
     curing
    -0.07
    POSITIVE LOGITS
    Bitcoin
    0.09
     saham
    0.09
    Stocks
    0.08
     zug
    0.08
    anser
    0.08
     blackjack
    0.08
     stocks
    0.08
    drawing
    0.08
     BTC
    0.08
    uites
    0.08
    Activations Density 0.010%

    No Known Activations