© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47896
    Prev
    Next
    INDEX
    Explanations

    1

    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
     tales
    -0.08
     Middleware
    -0.08
    	env
    -0.07
     Rules
    -0.07
     ET
    -0.07
     Reflection
    -0.07
     Mic
    -0.07
    env
    -0.07
    itches
    -0.07
     Integrated
    -0.07
    POSITIVE LOGITS
    煤
    0.10
    itized
    0.08
     raio
    0.08
    鞋
    0.08
    पछि
    0.08
    comed
    0.08
     площ
    0.08
     πλη
    0.08
     sauran
    0.07
    DVD
    0.07
    Activations Density 0.003%

    No Known Activations