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. 106201
    Prev
    Next
    INDEX
    Explanations

    ize

    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
     �
    -0.09
    -ton
    -0.09
     Cun
    -0.08
     SAC
    -0.08
     Taw
    -0.08
     ABD
    -0.08
     CW
    -0.08
     Gh
    -0.08
    meal
    -0.08
     Primera
    -0.08
    POSITIVE LOGITS
     bore
    0.08
    Van
    0.07
     scrum
    0.07
     оз
    0.07
    pick
    0.07
     MAT
    0.07
     е
    0.07
     ó
    0.07
     hed
    0.07
     দর্শ
    0.07
    Activations Density 0.099%

    No Known Activations