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. 15-RESID-POST-AA
    6. 19116
    Prev
    Next
    INDEX
    Explanations

    Internet snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -0.08
     deze
    -0.08
     aquesta
    -0.08
     "&
    -0.08
     ظاهر
    -0.08
     verw
    -0.08
     wannan
    -0.08
     Aliment
    -0.08
     its
    -0.08
     gerir
    -0.08
    POSITIVE LOGITS
    "),
    ↵
    0.08
    _);
    ↵
    0.08
    #+#+#+#+
    0.08
    #+#+
    0.08
    ʻau
    0.08
    �ి
    0.08
    _),
    0.08
    "),↵
    0.08
    หนึ่ง
    0.08
    ")
    ↵
    0.08
    Activations Density 0.027%

    No Known Activations