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. 23224
    Prev
    Next
    INDEX
    Explanations

    data collection methodology

    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
     competit
    -0.08
     Lagi
    -0.08
     minim
    -0.08
    battle
    -0.07
     Venus
    -0.07
     heroin
    -0.07
    Competitive
    -0.07
    Opponent
    -0.07
    Maint
    -0.07
    uthor
    -0.07
    POSITIVE LOGITS
    查看
    0.10
     spreadsheets
    0.09
    文件
    0.09
     өндір
    0.09
     verify
    0.09
     metrics
    0.08
    .metrics
    0.08
    .files
    0.08
     tangible
    0.08
    .file
    0.08
    Activations Density 0.028%

    No Known Activations