Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43906
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
    Helpful
    -0.10
     Instagram
    -0.10
     Elementor
    -0.10
    Adobe
    -0.09
     제공
    -0.09
     instagram
    -0.09
     ofrece
    -0.09
     awkward
    -0.09
     nonfiction
    -0.09
     enjoyable
    -0.09
    POSITIVE LOGITS
     simulation
    0.13
    Simulation
    0.13
     Simulation
    0.13
    模拟
    0.12
     timestep
    0.12
     sim
    0.11
     FIFO
    0.11
     simulated
    0.11
     simulate
    0.10
    simulation
    0.10
    Activations Density 0.015%

    No Known Activations