© 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. 110801
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

    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
     algunos
    -0.08
     diversification
    -0.08
    orek
    -0.08
     movimiento
    -0.08
     cerveza
    -0.08
     slam
    -0.08
     apoyo
    -0.07
    osy
    -0.07
    Exports
    -0.07
     destin
    -0.07
    POSITIVE LOGITS
     symptoms
    0.11
     symptômes
    0.10
     Symptoms
    0.10
     incapac
    0.10
     symptomen
    0.10
     Sympt
    0.09
     manifestations
    0.09
     Symptome
    0.09
     Danger
    0.09
     dizziness
    0.09
    Activations Density 0.013%

    No Known Activations