© 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 EvalsExportsinterp-engineNEWAPI 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. 21283
    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
     ».↵↵
    -0.11
    ******/↵
    -0.10
    ».↵
    -0.10
     алардын
    -0.09
     նրանց
    -0.09
    ******/
    -0.09
    ӣ
    -0.09
    آن
    -0.09
    ･･
    -0.09
    ・・・
    -0.09
    POSITIVE LOGITS
     being
    0.13
    being
    0.12
    都是
    0.12
     be
    0.12
     являются
    0.12
     become
    0.12
     belong
    0.11
     correspond
    0.11
     exist
    0.11
     constitute
    0.11
    Activations Density 0.062%

    No Known Activations