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. 90656
    Prev
    Next
    INDEX
    Explanations

    people's

    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
    /her
    -0.08
     seasonal
    -0.08
     Alexander
    -0.07
     Diego
    -0.07
     manipulating
    -0.07
     >>=
    -0.07
     persistent
    -0.07
     WIN
    -0.07
    .pad
    -0.07
     categor
    -0.07
    POSITIVE LOGITS
     Конститу
    0.08
     республика
    0.08
    常委
    0.08
     들어
    0.08
     chorus
    0.08
    (Resource
    0.07
    XAxis
    0.07
     मंत्रालय
    0.07
     custody
    0.07
    รู
    0.07
    Activations Density 0.007%

    No Known Activations