© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64032
    Prev
    Next
    INDEX
    Explanations

    Concrete forms and tape

    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
     autón
    -0.09
     authentication
    -0.09
    ుగు
    -0.08
     విశ
    -0.08
    արզ
    -0.08
    ↵
↵
    -0.08
     银河
    -0.08
     yal
    -0.08
     wholehearted
    -0.08
    觉
    -0.07
    POSITIVE LOGITS
     molds
    0.10
     tooling
    0.08
     temporary
    0.08
    模板
    0.08
     Lar
    0.07
     Templates
    0.07
     références
    0.07
     loan
    0.07
     Method
    0.07
     tijdelijke
    0.07
    Activations Density 0.016%

    No Known Activations