Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119371
    Prev
    Next
    INDEX
    Explanations

    trade regulations

    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
     casually
    -0.08
     хора
    -0.08
     içinde
    -0.08
     struč
    -0.08
     dalej
    -0.08
     �
    -0.07
     bespre
    -0.07
     кім
    -0.07
     અંદ
    -0.07
     знаход
    -0.07
    POSITIVE LOGITS
     tariffs
    0.10
    	export
    0.09
     impose
    0.09
     critères
    0.09
     imposed
    0.09
     regulations
    0.09
     экспорт
    0.09
    法规
    0.09
     പാല
    0.09
     tariff
    0.08
    Activations Density 0.011%

    No Known Activations