© 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. 64161
    Prev
    Next
    INDEX
    Explanations

    LU

    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
    polis
    -0.08
     polis
    -0.08
    _pol
    -0.08
     {[
    -0.08
     lawsuits
    -0.07
    श्रेष्ठ
    -0.07
     {(
    -0.07
     teknoloji
    -0.07
    (pol
    -0.07
     unders
    -0.07
    POSITIVE LOGITS
     tarde
    0.08
     شي
    0.08
    omod
    0.08
     Golf
    0.08
    šti
    0.08
     Scala
    0.07
    spannung
    0.07
     חי
    0.07
     ці
    0.07
     معم
    0.07
    Activations Density 0.002%

    No Known Activations