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. 120287
    Prev
    Next
    INDEX
    Explanations

    Code with mathematical expressions

    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
     Notify
    -0.09
    ノ
    -0.08
    �
    -0.08
     Comprehensive
    -0.08
     Quick
    -0.08
    IRS
    -0.07
     Millennium
    -0.07
     Comment
    -0.07
     Gro
    -0.07
     Multi
    -0.07
    POSITIVE LOGITS
     repression
    0.09
     budou
    0.09
     automation
    0.09
    _precision
    0.08
    antia
    0.08
    freq
    0.08
     Launcher
    0.08
    anguardia
    0.08
    _vari
    0.08
     desain
    0.08
    Activations Density 0.001%

    No Known Activations