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. 53245
    Prev
    Next
    INDEX
    Explanations

    distance

    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
    .dropdown
    -0.09
     piracy
    -0.08
     employees
    -0.08
     EObject
    -0.08
    办公
    -0.07
     depreciation
    -0.07
    双方
    -0.07
     swirling
    -0.07
     confusion
    -0.07
     직원
    -0.07
    POSITIVE LOGITS
     marathon
    0.13
     endurance
    0.11
     Marathon
    0.11
     мара
    0.11
     kilomet
    0.11
     arduous
    0.10
     perseverance
    0.09
     agon
    0.09
    athons
    0.09
     anspruch
    0.09
    Activations Density 0.033%

    No Known Activations