© 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. 96568
    Prev
    Next
    INDEX
    Explanations

    CIA and spying

    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
     Etsy
    -0.10
     barley
    -0.10
     apples
    -0.09
     pedals
    -0.09
     शिक्षक
    -0.09
     compost
    -0.09
     पौ
    -0.09
     fullness
    -0.09
     ग्राम
    -0.09
     फूल
    -0.08
    POSITIVE LOGITS
     espion
    0.28
     CIA
    0.24
     spies
    0.22
     clandest
    0.22
     covert
    0.22
     spy
    0.21
     intel
    0.20
     جاس
    0.20
    CIA
    0.20
     terrorist
    0.20
    Activations Density 0.104%

    No Known Activations