© 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. 96343
    Prev
    Next
    INDEX
    Explanations

    honesty

    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
     گردش
    -0.08
    érico
    -0.07
    _phy
    -0.07
     phosphory
    -0.07
    endidos
    -0.07
    157
    -0.07
     تشكيل
    -0.07
     Butterfly
    -0.07
    פע
    -0.07
    蝶
    -0.07
    POSITIVE LOGITS
     honesty
    0.46
     honest
    0.41
     honn
    0.41
    诚
    0.39
     truthful
    0.36
     eerlijk
    0.36
     Honest
    0.35
     чест
    0.34
     authenticity
    0.34
     ehrlich
    0.33
    Activations Density 0.176%

    No Known Activations