© 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. 11-RESID-POST-AA
    11. 78132
    Prev
    Next
    INDEX
    Explanations

    control

    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
     screened
    -0.08
     queries
    -0.08
     pretend
    -0.08
    ogl
    -0.07
    .Ap
    -0.07
     Tao
    -0.07
    /sc
    -0.07
     Boek
    -0.07
     constitu
    -0.07
    讯
    -0.07
    POSITIVE LOGITS
     geraten
    0.09
     fireworks
    0.08
     uncont
    0.08
     uncontrolled
    0.08
     abandono
    0.08
    arly
    0.08
     helpless
    0.07
     ganas
    0.07
     fent
    0.07
    589
    0.07
    Activations Density 0.018%

    No Known Activations