© 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. 3-RESID-POST-AA
    11. 2692
    Prev
    Next
    INDEX
    Explanations

    drop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    社会
    -0.08
     Sand
    -0.08
     �
    -0.08
     trains
    -0.07
    etha
    -0.07
    产业
    -0.07
     abrasive
    -0.07
    trip
    -0.07
     resort
    -0.07
    tren
    -0.07
    POSITIVE LOGITS
    ning
    0.08
    (edges
    0.08
     udp
    0.07
     initialize
    0.07
     BUT
    0.07
     dap
    0.07
     नक
    0.07
     couple
    0.07
     جام
    0.07
    /un
    0.07
    Activations Density 0.371%

    No Known Activations