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. 30513
    Prev
    Next
    INDEX
    Explanations

    create new resources

    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
    Intensity
    -0.08
     intensity
    -0.08
     interrogation
    -0.08
     adaptations
    -0.08
     ανα
    -0.07
     collected
    -0.07
     evening
    -0.07
    -hour
    -0.07
     der
    -0.07
     intensiv
    -0.07
    POSITIVE LOGITS
     신규
    0.15
     nuevos
    0.14
     नए
    0.14
     नई
    0.14
     الجديدة
    0.14
     nieuwe
    0.14
     new
    0.14
     नया
    0.14
     creation
    0.14
     नयाँ
    0.13
    Activations Density 0.029%

    No Known Activations