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. 54123
    Prev
    Next
    INDEX
    Explanations

    主题

    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
     enduring
    -0.08
    'lgan
    -0.07
     absorbing
    -0.07
    Uploader
    -0.07
     MLS
    -0.07
     kuku
    -0.07
    allu
    -0.07
    уш
    -0.07
     assortment
    -0.07
    shay
    -0.07
    POSITIVE LOGITS
     Nummer
    0.09
     Themen
    0.08
     подраздел
    0.08
     thematic
    0.08
     Thema
    0.08
    _num
    0.08
    /theme
    0.08
     излож
    0.08
     Trips
    0.08
     Themes
    0.08
    Activations Density 0.001%

    No Known Activations