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. 15-RESID-POST-AA
    6. 19135
    Prev
    Next
    INDEX
    Explanations

    summarization, GPT instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éventuellement
    -0.08
     commerce
    -0.08
     @_;↵
    -0.08
     ede
    -0.08
    hok
    -0.07
     få
    -0.07
     abar
    -0.07
     cellulose
    -0.07
     @_;↵↵
    -0.07
     potentially
    -0.07
    POSITIVE LOGITS
    五星
    0.08
    0.07
     cere
    0.07
    icient
    0.07
    .NOT
    0.07
    .metric
    0.07
    0.07
     正
    0.07
    .Fragment
    0.07
    .NON
    0.07
    Activations Density 0.006%

    No Known Activations