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. 111654
    Prev
    Next
    INDEX
    Explanations

    future

    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
     eerie
    -0.09
     attained
    -0.08
     되어
    -0.07
     된
    -0.07
     died
    -0.07
     ارزش
    -0.07
     بودن
    -0.07
     сектор
    -0.07
    �ు
    -0.07
     Poi
    -0.07
    POSITIVE LOGITS
    -proof
    0.09
     future
    0.08
    දී
    0.08
     futuro
    0.08
    .operations
    0.08
    _fn
    0.08
     futuros
    0.08
     কাজে
    0.08
     iterations
    0.08
     futurs
    0.08
    Activations Density 0.037%

    No Known Activations