© 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. 71052
    Prev
    Next
    INDEX
    Explanations

    quite

    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
     шара
    -0.09
     Becker
    -0.08
     mela
    -0.08
    vai
    -0.08
     aufs
    -0.08
     levy
    -0.08
     Amt
    -0.08
     Straf
    -0.08
     Corona
    -0.08
    掉
    -0.07
    POSITIVE LOGITS
     remarkable
    0.09
     frankly
    0.07
     ск
    0.07
    不错
    0.07
    しい
    0.07
     morale
    0.07
     لا
    0.07
    لاح
    0.07
    INU
    0.07
    .fixture
    0.07
    Activations Density 0.013%

    No Known Activations