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. 113870
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     neigh
    -0.08
     בבית
    -0.08
     stehen
    -0.08
     amarillo
    -0.08
    ást
    -0.07
     triturador
    -0.07
     黄
    -0.07
    ത്തില
    -0.07
     sart
    -0.07
     espero
    -0.07
    POSITIVE LOGITS
     shocks
    0.08
     market
    0.08
    ийн
    0.07
    .external
    0.07
    าค
    0.07
     influx
    0.07
    .unmodifiable
    0.07
     externe
    0.07
     calibration
    0.07
     externas
    0.07
    Activations Density 0.003%

    No Known Activations