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. 3-RESID-POST-AA
    6. 3001
    Prev
    Next
    INDEX
    Explanations

    这

    np_max-act · gemini-2.0-flash

    Chinese proximal demonstratives and simple numeral markers, especially when introducing noun phrases or section/list headings.

    oai_token-act-pair · gpt-5Triggered by @tatsatx
    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
     agh
    -0.08
     Aron
    -0.07
    -0.07
     Allan
    -0.07
     flare
    -0.07
    -0.07
     sech
    -0.07
     Robertson
    -0.07
     follic
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ın
    0.07
     لت
    0.07
    much
    0.07
    Vid
    0.07
     initials
    0.07
    낸
    0.07
    张
    0.07
     perme
    0.07
     않
    0.07
    Bolt
    0.07
    Activations Density 0.010%

    No Known Activations