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. 77373
    Prev
    Next
    INDEX
    Explanations

    python filepaths

    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
     الأم
    -0.08
    oise
    -0.08
    120
    -0.07
    115
    -0.07
     spare
    -0.07
     Spins
    -0.07
    ясь
    -0.07
     son's
    -0.07
     daughter's
    -0.07
     Spare
    -0.07
    POSITIVE LOGITS
     жок
    0.08
    ();
    ↵
    0.08
    (marker
    0.08
    Bom
    0.08
     convertido
    0.08
     onderhouden
    0.07
     সদস্য
    0.07
     verdu
    0.07
    Ago
    0.07
     туда
    0.07
    Activations Density 0.001%

    No Known Activations