© 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. 11-RESID-POST-AA
    11. 63110
    Prev
    Next
    INDEX
    Explanations

    Excerpts from larger content

    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
     mais
    -0.10
    ですが
    -0.10
    ，但是
    -0.09
    ，但
    -0.09
     ngunit
    -0.09
     하지만
    -0.09
     but
    -0.09
     MAIS
    -0.09
    But
    -0.08
     কিন্তু
    -0.08
    POSITIVE LOGITS
     మాత్రం
    0.15
    却
    0.13
     ändå
    0.13
     trotzdem
    0.11
     nonetheless
    0.11
    还是
    0.10
    仍
    0.10
     siiski
    0.10
     vẫn
    0.10
     dennoch
    0.10
    Activations Density 1.045%

    No Known Activations