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. 53810
    Prev
    Next
    INDEX
    Explanations

    (void

    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
     exped
    -0.08
    -off
    -0.08
     tang
    -0.08
    788
    -0.07
    three
    -0.07
     rush
    -0.07
    lack
    -0.07
    ప
    -0.07
    表
    -0.07
    箱
    -0.07
    POSITIVE LOGITS
     kuuluu
    0.09
     Moll
    0.09
     ote
    0.08
     Malik
    0.07
     طریق
    0.07
     comprend
    0.07
     Freddie
    0.07
     Malmö
    0.07
    <Data
    0.07
     Milli
    0.07
    Activations Density 0.000%

    No Known Activations