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. 29902
    Prev
    Next
    INDEX
    Explanations

    medication effects and timelines

    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
     retraite
    -0.08
     industriais
    -0.08
     נש
    -0.08
    ',$
    -0.08
    corner
    -0.08
    -0.07
     Hanover
    -0.07
    -mouth
    -0.07
     wild
    -0.07
     بالقرب
    -0.07
    POSITIVE LOGITS
     तुरंत
    0.11
     délai
    0.11
     onset
    0.11
     sooner
    0.11
    立即
    0.11
     inmediata
    0.11
     empezar
    0.11
     sofort
    0.10
     Immediate
    0.10
    多久
    0.10
    Activations Density 0.035%

    No Known Activations