© 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. 111470
    Prev
    Next
    INDEX
    Explanations

    2

    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
     denn
    -0.08
    itut
    -0.08
    urin
    -0.08
    ulan
    -0.07
     Ond
    -0.07
     Davenport
    -0.07
     lob
    -0.07
     Sú
    -0.07
    unik
    -0.07
     mant
    -0.07
    POSITIVE LOGITS
    直接
    0.08
     строки
    0.08
    フィール
    0.08
     строк
    0.08
     напрямую
    0.07
     ഗ്രാമ
    0.07
     gram
    0.07
     compre
    0.07
    айл
    0.07
     зол
    0.07
    Activations Density 0.007%

    No Known Activations