© 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. 51997
    Prev
    Next
    INDEX
    Explanations

    E

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ծ
    -0.09
     ****************
    -0.09
     Coverage
    -0.08
     která
    -0.08
     traslad
    -0.08
    /router
    -0.08
     tshaj
    -0.08
     ************************
    -0.08
     uygun
    -0.08
    ుకు
    -0.08
    POSITIVE LOGITS
    Heal
    0.08
    FE
    0.08
    All
    0.08
    Mutable
    0.07
    hein
    0.07
    Ф
    0.07
    ’è
    0.07
    Alla
    0.07
    Lo
    0.07
    Gra
    0.07
    Activations Density 0.001%

    No Known Activations