© 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. 19-RESID-POST-AA
    11. 21100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ხდება
    -0.10
    ýä
    -0.10
    ĝas
    -0.10
    านุการ
    -0.10
    лыгы
    -0.10
    .ต
    -0.10
    ènements
    -0.10
     LEDs
    -0.10
     հաստ
    -0.10
    .ศ
    -0.10
    POSITIVE LOGITS
    have
    0.11
    having
    0.10
    their
    0.10
    Have
    0.09
    tell
    0.09
    this
    0.09
    his
    0.09
     his
    0.09
    _HAVE
    0.08
    here
    0.08
    Activations Density 0.002%

    No Known Activations