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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108775
    Prev
    Next
    INDEX
    Explanations

    cytoskeleton

    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
     diploma
    -0.09
     Admissions
    -0.09
     diplôm
    -0.09
     rebut
    -0.09
     eficácia
    -0.08
     accreditation
    -0.08
    Revenue
    -0.08
    Emails
    -0.08
     Accreditation
    -0.08
     CDs
    -0.08
    POSITIVE LOGITS
    驱
    0.09
    家具
    0.09
     활
    0.08
    凝
    0.08
     energized
    0.08
     furniture
    0.08
     இயக்க
    0.08
    维护
    0.08
     घूम
    0.08
     Furniture
    0.08
    Activations Density 0.004%

    No Known Activations