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. 112397
    Prev
    Next
    INDEX
    Explanations

    tightness

    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
     Gecko
    -0.07
     seamlessly
    -0.07
     coping
    -0.07
     handling
    -0.07
    ebug
    -0.07
     runt
    -0.07
     compagnon
    -0.07
    /debug
    -0.07
     prag
    -0.07
     Emilio
    -0.07
    POSITIVE LOGITS
     scarcity
    0.11
     shortages
    0.10
     Demand
    0.10
     الطلب
    0.09
     narrowed
    0.09
     deficient
    0.09
     congest
    0.09
     scarce
    0.09
     خشک
    0.09
     ราค
    0.08
    Activations Density 0.022%

    No Known Activations