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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50095
    Prev
    Next
    INDEX
    Explanations

    diplomatic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     political
    -0.11
     السياسي
    -0.10
     الفكر
    -0.09
     سياسي
    -0.09
     geopolitical
    -0.09
     politieke
    -0.09
    Political
    -0.09
     Political
    -0.08
     philanthropic
    -0.08
     ideological
    -0.08
    POSITIVE LOGITS
     démarches
    0.16
     maneuver
    0.15
     mane
    0.13
     manoe
    0.13
     parle
    0.12
     calculus
    0.12
     calcula
    0.12
     gymnastics
    0.12
     calculations
    0.12
     계산
    0.11
    Activations Density 0.020%

    No Known Activations