© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 30320
    Prev
    Next
    INDEX
    Explanations

    DFS

    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
     midi
    -0.07
    સાર
    -0.07
     sober
    -0.07
     ji
    -0.07
    Joystick
    -0.07
     klaar
    -0.07
     bell
    -0.07
     unrest
    -0.07
    ਸ਼
    -0.07
    iano
    -0.07
    POSITIVE LOGITS
    Cot
    0.09
     cones
    0.08
     โปร
    0.08
    貼
    0.08
     Glacier
    0.08
    astien
    0.08
     Cotton
    0.08
     fuite
    0.08
     cone
    0.08
     Επι
    0.08
    Activations Density 0.000%

    No Known Activations