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. 111705
    Prev
    Next
    INDEX
    Explanations

    mindfulness

    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
    opi
    -0.08
     Shawn
    -0.07
     José
    -0.07
     Lieber
    -0.07
    upi
    -0.07
     pikir
    -0.07
     Webster
    -0.07
    affen
    -0.07
    rapie
    -0.07
     lingu
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.09
     publicly
    0.08
    -based
    0.08
     അടിസ്ഥാന
    0.08
    _PUBLIC
    0.08
    .all
    0.08
    .second
    0.08
     public
    0.08
     willingness
    0.08
     самостоятель
    0.08
    Activations Density 0.002%

    No Known Activations