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. 54185
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    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
    几十
    -0.08
     tor
    -0.08
    .reset
    -0.08
     scar
    -0.08
     prost
    -0.08
     skeleton
    -0.08
    .separator
    -0.08
     koris
    -0.07
    .dark
    -0.07
     ||=
    -0.07
    POSITIVE LOGITS
     Louisiana
    0.09
    race
    0.08
     Leon
    0.08
     Senator
    0.08
     emperor
    0.08
    fruit
    0.08
     Pope
    0.08
    Batman
    0.08
     Zeus
    0.08
    President
    0.08
    Activations Density 0.005%

    No Known Activations