© 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. 950
    Prev
    Next
    INDEX
    Explanations

    C++ constructors

    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
     Renewable
    -0.08
     압
    -0.08
    .OR
    -0.08
     sprem
    -0.07
     realtà
    -0.07
    (tv
    -0.07
    .orange
    -0.07
    Reusable
    -0.07
     stressing
    -0.07
     ligament
    -0.07
    POSITIVE LOGITS
    อื่น
    0.08
    аличие
    0.07
     pregunta
    0.07
     texas
    0.07
     Text
    0.07
     Formular
    0.07
     lom
    0.07
     presence
    0.07
     facilidad
    0.07
     autod
    0.07
    Activations Density 0.001%

    No Known Activations