© 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. 52190
    Prev
    Next
    INDEX
    Explanations

    Converting numbers into words

    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
    ១០
    -0.11
    ૦
    -0.10
    ២
    -0.10
    ០
    -0.10
     รอบ
    -0.09
    өкүм
    -0.09
     લગભગ
    -0.09
    ১২
    -0.09
    ១
    -0.09
     فبراير
    -0.09
    POSITIVE LOGITS
    point
    0.14
     point
    0.13
     Point
    0.13
    ty
    0.12
    _point
    0.12
    .point
    0.12
    Point
    0.12
    y
    0.11
    nty
    0.11
    -h
    0.10
    Activations Density 0.011%

    No Known Activations