© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 52077
    Prev
    Next
    INDEX
    Explanations

    last names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Espírito
    -0.10
     Për
    -0.08
     midi
    -0.08
     Perspekt
    -0.08
     Tac
    -0.08
     Hải
    -0.08
    jál
    -0.08
     �
    -0.08
    теп
    -0.07
    poj
    -0.07
    POSITIVE LOGITS
    inniss
    0.13
    aughty
    0.12
    ough
    0.11
    onnell
    0.11
    iece
    0.11
    weeney
    0.11
    raith
    0.11
    ulty
    0.11
    innon
    0.10
    arty
    0.10
    Activations Density 0.014%

    No Known Activations