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. 53102
    Prev
    Next
    INDEX
    Explanations

    留

    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
     eros
    -0.08
    initions
    -0.08
    hetic
    -0.07
    IMUM
    -0.07
     SEC
    -0.07
    Interrupted
    -0.07
    /her
    -0.07
     fet
    -0.07
    _FILE
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    烟
    0.08
    Bew
    0.08
     रहें
    0.08
    疑
    0.08
     रहती
    0.07
     dran
    0.07
     apologized
    0.07
     रहते
    0.07
    Pier
    0.07
     Pern
    0.07
    Activations Density 0.004%

    No Known Activations