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. 59547
    Prev
    Next
    INDEX
    Explanations

    paradoxes

    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
     screen
    -0.07
     ona
    -0.07
     lifestyle
    -0.07
     wants
    -0.07
     additional
    -0.07
     ഏ
    -0.07
    -0.07
     empre
    -0.07
     logistics
    -0.07
     Screen
    -0.07
    POSITIVE LOGITS
     surpre
    0.12
     deceptive
    0.12
     неожидан
    0.12
     paradox
    0.11
     ironic
    0.11
     fooled
    0.10
     violating
    0.10
    却
    0.10
     એવા
    0.10
     falsely
    0.10
    Activations Density 0.022%

    No Known Activations