© 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. 51989
    Prev
    Next
    INDEX
    Explanations

    folk

    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
    ่อง
    -0.08
    حدى
    -0.08
     Frühstück
    -0.08
     bedrijfs
    -0.07
     gesteld
    -0.07
     גוף
    -0.07
     fiscale
    -0.07
    ктив
    -0.07
    焦
    -0.07
    қты
    -0.07
    POSITIVE LOGITS
    ishly
    0.14
    estone
    0.14
    ways
    0.14
    spraak
    0.12
    ships
    0.12
    lo
    0.12
    song
    0.12
    ish
    0.12
     flest
    0.11
     tales
    0.11
    Activations Density 0.011%

    No Known Activations