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. 58368
    Prev
    Next
    INDEX
    Explanations

    Core Data stack

    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
     chase
    -0.08
     warfare
    -0.07
     Warfare
    -0.07
     inhibition
    -0.07
    resso
    -0.07
    στο
    -0.07
     convertir
    -0.07
    -counter
    -0.07
    price
    -0.07
     chasing
    -0.07
    POSITIVE LOGITS
    设施
    0.10
     называется
    0.09
     acord
    0.09
    贴吧
    0.08
    (Server
    0.08
    _initialized
    0.08
    енных
    0.08
     играет
    0.08
     verd
    0.08
    施設
    0.08
    Activations Density 0.001%

    No Known Activations