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. 58641
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
    _arguments
    -0.09
    .arguments
    -0.08
     ponta
    -0.08
    .Localization
    -0.07
    weich
    -0.07
     Approximately
    -0.07
    ట్టి
    -0.07
     понад
    -0.07
    Antwort
    -0.07
     Перед
    -0.07
    POSITIVE LOGITS
    /DVD
    0.08
    'il
    0.08
     rinc
    0.08
     �
    0.08
     rend
    0.08
    ’il
    0.07
    -final
    0.07
     invit
    0.07
    /foo
    0.07
    /f
    0.07
    Activations Density 0.058%

    No Known Activations