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. 11887
    Prev
    Next
    INDEX
    Explanations

    acting, actors

    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
     quorum
    -0.10
    .units
    -0.09
    .storage
    -0.09
     almacen
    -0.09
     магнит
    -0.09
    _entropy
    -0.08
     magnets
    -0.08
     магазин
    -0.08
    Entropy
    -0.08
    -0.08
    POSITIVE LOGITS
    主演
    0.16
    出演
    0.15
    演员
    0.15
     अभिनय
    0.15
     நடிக
    0.15
     நடித்த
    0.14
     अभिनेत्री
    0.14
     അഭിനയ
    0.14
     actress
    0.14
     ನಟ
    0.13
    Activations Density 0.179%

    No Known Activations