© 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. 114303
    Prev
    Next
    INDEX
    Explanations

    Atrial fibrillation

    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
     selectie
    -0.07
     prescription
    -0.07
     locatie
    -0.07
    機
    -0.07
     preservatives
    -0.07
    ள
    -0.07
     garantie
    -0.07
     museums
    -0.07
     petroleum
    -0.07
    enschutz
    -0.07
    POSITIVE LOGITS
     velocidades
    0.08
     volley
    0.08
    .pitch
    0.08
    collapse
    0.08
     collapse
    0.08
     Ina
    0.08
     broom
    0.08
     Steph
    0.08
     والمد
    0.08
     Impro
    0.08
    Activations Density 0.002%

    No Known Activations