© 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. 108171
    Prev
    Next
    INDEX
    Explanations

    sine waves

    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
    jun
    -0.08
     ઝ
    -0.08
    Observable
    -0.08
    \application
    -0.08
    快
    -0.07
     Complete
    -0.07
    _nn
    -0.07
    非
    -0.07
     Evangel
    -0.07
    Complete
    -0.07
    POSITIVE LOGITS
     Wrist
    0.09
     wrist
    0.08
    Desk
    0.08
    988
    0.08
    оид
    0.08
    ride
    0.07
     kész
    0.07
     fare
    0.07
     walkthrough
    0.07
     출장
    0.07
    Activations Density 0.003%

    No Known Activations