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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78554
    Prev
    Next
    INDEX
    Explanations

    legal arguments

    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
     лучшие
    -0.08
    IENTO
    -0.07
     Suites
    -0.07
    送りします
    -0.07
    умо
    -0.07
    .Art
    -0.07
    Wise
    -0.07
    ження
    -0.07
     empowering
    -0.07
    'um
    -0.07
    POSITIVE LOGITS
     hk
    0.08
     offen
    0.08
    λη
    0.08
    程序
    0.07
     latent
    0.07
     sr
    0.07
     depr
    0.07
     lait
    0.07
    Lat
    0.07
    ISING
    0.07
    Activations Density 0.002%

    No Known Activations