Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44979
    Prev
    Next
    INDEX
    Explanations

    Little Red Riding Hood

    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
     DAO
    -0.08
     hive
    -0.08
     oui
    -0.08
     imdb
    -0.08
     rov
    -0.08
    -0.07
     реализации
    -0.07
    -0.07
     дека
    -0.07
     spettac
    -0.07
    POSITIVE LOGITS
     medd
    0.08
     aparecen
    0.08
     क्रममा
    0.08
    님의
    0.08
     Tale
    0.08
     등장
    0.08
    .Filter
    0.07
    溪
    0.07
     encontraron
    0.07
    .Rem
    0.07
    Activations Density 0.001%

    No Known Activations