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. 13028
    Prev
    Next
    INDEX
    Explanations

    Online exam proctoring

    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
    ্প
    -0.08
     enable
    -0.08
     prò
    -0.08
     grat
    -0.08
     prognosis
    -0.07
    classification
    -0.07
    crip
    -0.07
     prevail
    -0.07
     humor
    -0.07
     Scotland
    -0.07
    POSITIVE LOGITS
     esit
    0.08
     monitored
    0.08
     aérea
    0.08
     �
    0.08
     लाइव
    0.08
     filmed
    0.08
     Delivered
    0.08
     Answers
    0.08
    Verified
    0.08
     inspections
    0.08
    Activations Density 0.005%

    No Known Activations