© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94544
    Prev
    Next
    INDEX
    Explanations

    automotive industry

    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
    -resource
    -0.08
     Resource
    -0.08
     verzekerd
    -0.08
    .Resource
    -0.08
    .resource
    -0.08
     MPH
    -0.08
     resource
    -0.08
     hazards
    -0.08
    /resource
    -0.08
     spells
    -0.08
    POSITIVE LOGITS
    Manufacturer
    0.10
     fabricar
    0.10
    Manufact
    0.10
     تصنيع
    0.10
     выпуска
    0.10
    制造
    0.10
    assemble
    0.10
     manuf
    0.10
     Herstell
    0.10
     manufacturing
    0.09
    Activations Density 0.071%

    No Known Activations