© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113640
    Prev
    Next
    INDEX
    Explanations

    File

    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
    忧
    -0.08
    Variable
    -0.08
    Sending
    -0.08
     hauling
    -0.08
    Modified
    -0.08
     uneasy
    -0.07
    iza
    -0.07
     Тогда
    -0.07
    乱
    -0.07
    332
    -0.07
    POSITIVE LOGITS
     _.
    0.08
     inflation
    0.08
     annex
    0.08
    amani
    0.08
    explode
    0.08
     URLs
    0.07
    _.
    0.07
     SJ
    0.07
     Oven
    0.07
     decid
    0.07
    Activations Density 0.000%

    No Known Activations