© 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. 19880
    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
     etwa
    -0.08
    _safe
    -0.07
     adequate
    -0.07
    _er
    -0.07
     life
    -0.07
    _i
    -0.07
     நல்ல
    -0.07
    राब
    -0.07
     Life
    -0.07
    er
    -0.07
    POSITIVE LOGITS
     алын
    0.11
    guigu
    0.11
     geschreven
    0.10
     эсеп
    0.10
     వచ్చిన
    0.09
    ileyo
    0.09
     gezet
    0.09
     алған
    0.09
     copied
    0.09
     қарап
    0.09
    Activations Density 0.000%

    No Known Activations