Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11939
    Prev
    Next
    INDEX
    Explanations

    dorsolateral prefrontal cortex

    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
     של
    -0.08
     Halt
    -0.07
     disasters
    -0.07
    Parms
    -0.07
     creator
    -0.07
     streamer
    -0.07
     persecution
    -0.07
    級
    -0.07
     webcast
    -0.07
     gigantic
    -0.07
    POSITIVE LOGITS
     cortex
    0.13
     cortical
    0.10
     Cortex
    0.10
     regions
    0.10
     моз
    0.10
     frontal
    0.09
     serotonin
    0.09
     područ
    0.09
    肌
    0.09
     dorsal
    0.09
    Activations Density 0.004%

    No Known Activations