© 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. 68800
    Prev
    Next
    INDEX
    Explanations

    irrational numbers and math

    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
    placements
    -0.08
    装备
    -0.08
     healing
    -0.08
    .button
    -0.08
     sensitiv
    -0.07
     helicopters
    -0.07
     lineback
    -0.07
    -0.07
     rigtig
    -0.07
    Healing
    -0.07
    POSITIVE LOGITS
     irrational
    0.15
     Rational
    0.11
    finite
    0.11
     mathematic
    0.11
     finite
    0.11
     Famous
    0.11
     rational
    0.10
     infinite
    0.10
     finit
    0.10
    Finite
    0.10
    Activations Density 0.019%
    No Known Activations