© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44447
    Prev
    Next
    INDEX
    Explanations

    Goldbach Conjecture

    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
     скид
    -0.08
     Bogotá
    -0.08
     tinta
    -0.08
     бю
    -0.08
    شارة
    -0.08
     Patagonia
    -0.07
    फोन
    -0.07
     sead
    -0.07
    kwọ
    -0.07
     Madagascar
    -0.07
    POSITIVE LOGITS
     conject
    0.11
     everyone's
    0.08
     hardest
    0.08
     unresolved
    0.08
     conspiracy
    0.07
     strengthening
    0.07
     Alzheimer's
    0.07
     wording
    0.07
     kof
    0.07
     fortalecer
    0.07
    Activations Density 0.006%

    No Known Activations