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. 54278
    Prev
    Next
    INDEX
    Explanations

    code and memory-related

    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
    (Media
    -0.08
    quartered
    -0.08
    同比
    -0.08
     multinational
    -0.08
     quarterly
    -0.08
     NATO
    -0.08
     Siri
    -0.08
    ออนไลน์
    -0.08
     Nutr
    -0.07
    (Matrix
    -0.07
    POSITIVE LOGITS
     обход
    0.09
     trecho
    0.09
     anchor
    0.09
     Execut
    0.08
     unreachable
    0.08
     reachable
    0.08
     astore
    0.08
     ambience
    0.08
    yllic
    0.08
     lloc
    0.08
    Activations Density 0.002%

    No Known Activations