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. 75888
    Prev
    Next
    INDEX
    Explanations

    Financial data/discussions

    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
    իւ
    -0.09
    ոք
    -0.09
    דורך
    -0.09
    եժ
    -0.08
     შენი
    -0.08
    րա
    -0.08
    真实吗
    -0.08
    trituradora
    -0.08
     rejoint
    -0.08
    յուր
    -0.08
    POSITIVE LOGITS
    .Question
    0.08
     QPush
    0.07
     Nm
    0.07
    .Allow
    0.07
     nond
    0.07
    .Interfaces
    0.07
    .T
    0.07
     engineering
    0.07
     Ambul
    0.07
    :R
    0.07
    Activations Density 0.000%

    No Known Activations