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. 98274
    Prev
    Next
    INDEX
    Explanations

    T

    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
     മര
    -0.09
    finish
    -0.08
    content
    -0.08
    cline
    -0.08
     finish
    -0.08
     nội
    -0.07
    inion
    -0.07
     Brasile
    -0.07
    etable
    -0.07
    retched
    -0.07
    POSITIVE LOGITS
     наоборот
    0.09
    로벌
    0.08
     confiar
    0.08
    رت
    0.08
    وظ
    0.08
    יבה
    0.08
    交换
    0.07
    ุ
    0.07
    Delegate
    0.07
    יבת
    0.07
    Activations Density 0.000%

    No Known Activations