Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119193
    Prev
    Next
    INDEX
    Explanations

    Math problems with 'e'

    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
    ocr
    -0.08
     pressup
    -0.08
     nominal
    -0.07
     Wiley
    -0.07
     straps
    -0.07
     biomechanics
    -0.07
     perpendicular
    -0.07
     igre
    -0.07
    {lng
    -0.07
     planes
    -0.07
    POSITIVE LOGITS
    indent
    0.09
    ’ind
    0.08
    (www
    0.08
    indice
    0.07
    Fuse
    0.07
    咖
    0.07
    816
    0.07
     utilisateur
    0.07
    粒
    0.07
     Mayer
    0.07
    Activations Density 0.021%

    No Known Activations