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. 43710
    Prev
    Next
    INDEX
    Explanations

    fill-in-the-blank questions

    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
     kandid
    -0.08
    erv
    -0.08
    continental
    -0.07
    etry
    -0.07
    -election
    -0.07
    ()){
    ↵
    -0.07
     metropolitan
    -0.07
    geme
    -0.07
     orthodox
    -0.07
     fares
    -0.07
    POSITIVE LOGITS
    Template
    0.09
     template
    0.08
    ოდ
    0.08
    模板
    0.08
    .choose
    0.07
     বাক
    0.07
    句
    0.07
     plugging
    0.07
     blanks
    0.07
    .Template
    0.07
    Activations Density 0.070%

    No Known Activations