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. 421
    Prev
    Next
    INDEX
    Explanations

    to

    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
     obama
    -0.08
    'autor
    -0.07
    Gov
    -0.07
    Toolkit
    -0.07
    96
    -0.07
    manual
    -0.07
     Obama's
    -0.07
    Wp
    -0.07
     Manual
    -0.07
     Cat
    -0.07
    POSITIVE LOGITS
     lifespan
    0.10
     deaths
    0.09
     longevity
    0.09
    ecycle
    0.08
    生命周期
    0.08
     diagnosis
    0.08
     axle
    0.08
     veteran
    0.08
     lifecycle
    0.08
    ystal
    0.08
    Activations Density 0.006%

    No Known Activations