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. 65060
    Prev
    Next
    INDEX
    Explanations

    vim

    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
    研发
    -0.09
    环保
    -0.09
    ائح
    -0.08
    一路
    -0.08
    的网站
    -0.08
     jsonify
    -0.08
    旁
    -0.08
    热线
    -0.08
     pcl
    -0.08
     סיפ
    -0.07
    POSITIVE LOGITS
     Vim
    0.11
     vim
    0.10
    vim
    0.09
     Alive
    0.08
    Wiki
    0.08
     Photoshop
    0.08
    .os
    0.08
     mag
    0.08
     oss
    0.08
     bait
    0.08
    Activations Density 0.002%

    No Known Activations