Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43837
    Prev
    Next
    INDEX
    Explanations

    spiral

    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
     वृद्ध
    -0.08
     artır
    -0.08
     αύ
    -0.08
     awal
    -0.08
     Aw
    -0.08
     بڑھ
    -0.08
     Servers
    -0.07
     formulation
    -0.07
     allar
    -0.07
    交易
    -0.07
    POSITIVE LOGITS
    替
    0.09
     hose
    0.08
     convertido
    0.08
    患者
    0.08
    破解
    0.08
     SUBSTITUTE
    0.08
    _patient
    0.08
     破解
    0.08
     hoses
    0.08
    _dataframe
    0.08
    Activations Density 0.002%

    No Known Activations