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. 43989
    Prev
    Next
    INDEX
    Explanations

    color codes

    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
     literal
    -0.07
    Latch
    -0.07
    _literal
    -0.07
     movie
    -0.07
    stücke
    -0.07
    ச்
    -0.07
     fol
    -0.07
     Shower
    -0.07
     anecdotes
    -0.07
    弱
    -0.07
    POSITIVE LOGITS
     Arial
    0.09
    ర్స్
    0.08
     dezelfde
    0.08
    压
    0.08
     bono
    0.08
     serif
    0.08
     Rijn
    0.08
     TIFF
    0.07
    ేట
    0.07
     Siv
    0.07
    Activations Density 0.003%

    No Known Activations