© 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. 7-RESID-POST-AA
    11. 1125
    Prev
    Next
    INDEX
    Explanations

    loss of consciousness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ivy
    -0.07
    いつ
    -0.07
     현실
    -0.07
     пон
    -0.07
    Foundation
    -0.07
    /b
    -0.07
     bolet
    -0.07
     eternity
    -0.07
     אחרי
    -0.07
     notifier
    -0.07
    POSITIVE LOGITS
     Ac
    0.08
    deny
    0.08
     edən
    0.07
     hostility
    0.07
    0.07
    切
    0.07
     işlet
    0.07
     kalian
    0.07
     reluct
    0.07
     Cent
    0.07
    Activations Density 0.007%
    No Known Activations