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. 120154
    Prev
    Next
    INDEX
    Explanations

    Code deployment/execution settings

    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
     wkoll
    -0.09
     annað
    -0.09
     ие
    -0.09
     kiek
    -0.09
     überzeugt
    -0.09
    胆码
    -0.09
    რძნობ
    -0.09
     handsome
    -0.09
     άλλο
    -0.09
     પડી
    -0.09
    POSITIVE LOGITS
    education
    0.08
    Ful
    0.08
     Education
    0.08
    nil
    0.07
     Nil
    0.07
     trip
    0.07
    Education
    0.07
     nil
    0.07
     education
    0.07
    Gem
    0.07
    Activations Density 0.000%

    No Known Activations