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. 112620
    Prev
    Next
    INDEX
    Explanations

    non-English languages

    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
    ,根据
    -0.09
    ,仅
    -0.09
     kau
    -0.08
    ,为
    -0.07
    ,从
    -0.07
    据
    -0.07
    ику
    -0.07
    试看
    -0.07
    根据
    -0.07
    мат
    -0.07
    POSITIVE LOGITS
    \Carbon
    0.07
    spann
    0.07
    [((
    0.07
     followed
    0.07
    ٌ
    0.07
     Follow
    0.07
    follow
    0.07
    ipo
    0.07
    [href
    0.07
    analytics
    0.07
    Activations Density 0.146%

    No Known Activations