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. 77553
    Prev
    Next
    INDEX
    Explanations

    time

    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
     artık
    -0.07
    -limit
    -0.07
    List
    -0.07
     공
    -0.07
    Failures
    -0.07
     heißt
    -0.07
     결
    -0.07
     للج
    -0.07
     जोर
    -0.07
    	List
    -0.07
    POSITIVE LOGITS
     dauern
    0.11
    才能
    0.10
     lenta
    0.09
     accl
    0.09
     зато
    0.08
     aega
    0.08
     gradual
    0.08
     വേണ്ട
    0.08
    മയം
    0.08
    ご了承ください
    0.08
    Activations Density 0.049%

    No Known Activations