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. 77354
    Prev
    Next
    INDEX
    Explanations

    software installation and packages

    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
     ruido
    -0.09
    deg
    -0.09
    备注
    -0.09
    Radians
    -0.08
     listened
    -0.08
     bruit
    -0.08
     сексу
    -0.08
    Heading
    -0.08
     의견
    -0.08
    .sensor
    -0.08
    POSITIVE LOGITS
     tooling
    0.11
     Tools
    0.10
    工具
    0.09
     tools
    0.09
     Mole
    0.09
    .tools
    0.09
    _tools
    0.09
     mechanism
    0.08
    .Loader
    0.08
     ابزار
    0.08
    Activations Density 0.032%

    No Known Activations