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. 114006
    Prev
    Next
    INDEX
    Explanations

    morph

    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
    帯
    -0.08
    bolt
    -0.08
    сл
    -0.08
    ский
    -0.07
     Sun
    -0.07
    worthiness
    -0.07
    住所
    -0.07
    elsey
    -0.07
     Christophe
    -0.07
    Ordered
    -0.07
    POSITIVE LOGITS
     оч
    0.09
     jaw
    0.08
     Jaw
    0.07
     teasing
    0.07
     Fas
    0.07
     hình
    0.07
    案件
    0.07
     sham
    0.07
     இர
    0.07
     teaser
    0.07
    Activations Density 0.010%

    No Known Activations