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. 56129
    Prev
    Next
    INDEX
    Explanations

    machine learning kernels

    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
     numbered
    -0.10
     emergency
    -0.09
     staffed
    -0.08
    _trim
    -0.08
    -danger
    -0.08
     прил
    -0.08
    Emergency
    -0.08
     apprentices
    -0.08
     слово
    -0.08
     twenties
    -0.08
    POSITIVE LOGITS
     kernel
    0.13
     kernels
    0.12
     Kernel
    0.11
    Kernel
    0.11
     Kern
    0.10
    _kernel
    0.10
    kernel
    0.10
    .kernel
    0.10
    (kernel
    0.10
     Custom
    0.09
    Activations Density 0.003%

    No Known Activations