© 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. 23-RESID-POST-AA
    11. 49195
    Prev
    Next
    INDEX
    Explanations

    Embarrassment

    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
     screaming
    -0.08
     screamed
    -0.08
     nihil
    -0.08
     alleging
    -0.08
     السل
    -0.07
     screams
    -0.07
     yelled
    -0.07
     pahu
    -0.07
     sze
    -0.07
     scream
    -0.07
    POSITIVE LOGITS
     embarrassed
    0.18
     embarrassment
    0.17
     शर्म
    0.16
     shy
    0.16
    羞
    0.15
     sincerity
    0.13
     blush
    0.13
     bash
    0.13
     trochu
    0.13
     playful
    0.13
    Activations Density 0.072%

    No Known Activations