© 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. 25023
    Prev
    Next
    INDEX
    Explanations

    factories

    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
     Helvetica
    -0.09
    <header
    -0.09
    导航
    -0.09
    _Header
    -0.08
     Conversation
    -0.08
     traveled
    -0.08
     UINavigation
    -0.08
    	header
    -0.08
    Teleport
    -0.08
     teleport
    -0.08
    POSITIVE LOGITS
     시설
    0.17
     مصنع
    0.16
    设施
    0.15
     usine
    0.15
    生产
    0.15
    facility
    0.15
     facilities
    0.15
     manufacturing
    0.15
     производства
    0.14
    厂
    0.14
    Activations Density 0.146%

    No Known Activations