© 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. 25223
    Prev
    Next
    INDEX
    Explanations

    topic, off-topic

    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
     Patterns
    -0.08
    viet
    -0.08
     favored
    -0.08
     glow
    -0.08
     through
    -0.07
     monoxide
    -0.07
     verschiedener
    -0.07
    INST
    -0.07
     preko
    -0.07
     dann
    -0.07
    POSITIVE LOGITS
     estrict
    0.09
     tangent
    0.09
     tang
    0.09
     Jun
    0.09
     BER
    0.09
     Tang
    0.09
     допуст
    0.08
     hed
    0.08
     unrelated
    0.08
     irrelevant
    0.08
    Activations Density 0.009%

    No Known Activations