© 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. 11-RESID-POST-AA
    11. 91456
    Prev
    Next
    INDEX
    Explanations

    China

    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
     conse
    -0.09
    ho
    -0.08
     সূ
    -0.08
     Slip
    -0.08
    hips
    -0.08
     Diablo
    -0.08
    ocities
    -0.08
    conto
    -0.08
     Bruno
    -0.07
     бих
    -0.07
    POSITIVE LOGITS
    大陆
    0.14
    .alibaba
    0.09
    ：中国
    0.08
     era
    0.08
    共产党
    0.08
    科学院
    0.08
     Jinping
    0.08
     Yang
    0.08
     Alibaba
    0.08
    十大
    0.08
    Activations Density 0.023%

    No Known Activations