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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18500
    Prev
    Next
    INDEX
    Explanations

    internal

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ာင္
    -0.09
    ုပ်
    -0.08
    ၈
    -0.08
    =array
    -0.08
    'informations
    -0.08
    animals
    -0.08
     customise
    -0.08
    _cells
    -0.08
    Arrays
    -0.08
    modifiable
    -0.08
    POSITIVE LOGITS
     sqrt
    0.10
     radial
    0.09
     quadrant
    0.09
     ray
    0.09
     triangle
    0.09
     IB
    0.08
     angular
    0.08
     (?)
    0.08
     Mil
    0.08
     extreme
    0.08
    Activations Density 0.002%

    No Known Activations