© 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. 11-RESID-POST-AA
    6. 91520
    Prev
    Next
    INDEX
    Explanations

    code, hardware, software

    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
     marathon
    -0.11
     Airbnb
    -0.10
    _pickle
    -0.09
     mozzarella
    -0.09
     Goodreads
    -0.08
     Handmade
    -0.08
     moll
    -0.08
     rompe
    -0.08
    _runner
    -0.08
    心理
    -0.08
    POSITIVE LOGITS
     FPGA
    0.13
     VGA
    0.13
    (clk
    0.12
     selectable
    0.12
    posedge
    0.11
     transistor
    0.11
     NAND
    0.11
     बिट
    0.11
     UART
    0.11
     Arbitration
    0.11
    Activations Density 0.019%

    No Known Activations