© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7706
    Prev
    Next
    INDEX
    Explanations

    nail

    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
    迪
    -0.08
    甜
    -0.08
    ierra
    -0.08
    lector
    -0.08
     dés
    -0.07
    Topo
    -0.07
     beacon
    -0.07
    -0.07
     rech
    -0.07
     Terre
    -0.07
    POSITIVE LOGITS
     hammered
    0.09
    Forg
    0.09
     reparación
    0.09
    Written
    0.08
     nails
    0.08
    -hole
    0.08
    Helper
    0.08
     ремонта
    0.08
     outpatient
    0.07
     Inflation
    0.07
    Activations Density 0.005%

    No Known Activations