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. 43847
    Prev
    Next
    INDEX
    Explanations

    rigorous

    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
     kiếm
    -0.09
     Kür
    -0.08
     이미
    -0.08
    _password
    -0.08
     Bedien
    -0.08
     Venice
    -0.08
     lezot
    -0.08
     employing
    -0.08
     grooming
    -0.08
    iada
    -0.08
    POSITIVE LOGITS
     rigor
    0.10
     formal
    0.10
     formally
    0.10
    Formal
    0.08
     Formal
    0.08
     دقیق
    0.08
     rigorous
    0.08
     precise
    0.08
     nale
    0.08
     ю
    0.07
    Activations Density 0.008%

    No Known Activations