© 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. 110419
    Prev
    Next
    INDEX
    Explanations

    Study/Travel abroad

    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
    ifrån
    -0.08
     recharge
    -0.07
     masker
    -0.07
     vehicle
    -0.07
     nouveau
    -0.07
    _uint
    -0.07
     modalità
    -0.07
    .car
    -0.07
     persoon
    -0.07
    Advert
    -0.07
    POSITIVE LOGITS
     imobili
    0.08
     یافت
    0.08
    (Border
    0.08
     Regal
    0.08
     Heim
    0.07
     turmoil
    0.07
     motel
    0.07
    皇
    0.07
     നേടി
    0.07
     dramat
    0.07
    Activations Density 0.128%

    No Known Activations