© 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 EvalsExportsinterp-engineNEWAPI 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. 114108
    Prev
    Next
    INDEX
    Explanations

    workout nutrition

    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
     pressures
    -0.07
     arquivo
    -0.07
     inför
    -0.07
     archivo
    -0.07
    обор
    -0.07
     ubr
    -0.07
    그램
    -0.07
     quảng
    -0.07
    험
    -0.07
    /process
    -0.07
    POSITIVE LOGITS
     rehabilitation
    0.10
     Reconstruction
    0.09
     reconstruction
    0.09
     restorative
    0.09
     spätestens
    0.08
     repentance
    0.08
     reconciliation
    0.08
    Nutrition
    0.08
     snacks
    0.08
     nutritious
    0.08
    Activations Density 0.004%

    No Known Activations