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. 90249
    Prev
    Next
    INDEX
    Explanations

    bound

    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
     chile
    -0.08
     kategori
    -0.08
     categoria
    -0.08
    -focus
    -0.08
     خدمة
    -0.08
    kategori
    -0.07
     lave
    -0.07
    _categoria
    -0.07
     lush
    -0.07
     सिं
    -0.07
    POSITIVE LOGITS
     obviously
    0.09
    և
    0.08
     Peb
    0.08
    .ceil
    0.08
    .Part
    0.08
    .floor
    0.08
    ウォ
    0.08
    _ATT
    0.08
     כמובן
    0.07
     impede
    0.07
    Activations Density 0.021%

    No Known Activations