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. 30516
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     acreage
    -0.08
     imposto
    -0.08
     acre
    -0.08
    arih
    -0.08
     plead
    -0.08
    ற்கு
    -0.08
    Voxel
    -0.08
    _query
    -0.07
     children's
    -0.07
    REN
    -0.07
    POSITIVE LOGITS
     drum
    0.09
     �
    0.08
    gif
    0.08
     Drum
    0.08
    酒
    0.08
    جل
    0.07
    ja
    0.07
     GIF
    0.07
     직
    0.07
     drums
    0.07
    Activations Density 0.038%

    No Known Activations