© 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. 63562
    Prev
    Next
    INDEX
    Explanations

    migraines

    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
     мән
    -0.08
     abruptly
    -0.08
     patiently
    -0.08
     indef
    -0.08
    .Usuario
    -0.08
    .Device
    -0.08
     بور
    -0.07
     FIR
    -0.07
    sas
    -0.07
     hierro
    -0.07
    POSITIVE LOGITS
    agen
    0.07
    κού
    0.07
    iclo
    0.07
     prohibited
    0.07
     taboo
    0.07
     trig
    0.07
     banned
    0.07
     cognitive
    0.07
    achen
    0.07
     popping
    0.07
    Activations Density 0.002%

    No Known Activations