© 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. 19110
    Prev
    Next
    INDEX
    Explanations

    say "% or &"

    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
     чоң
    -0.08
    (mapped
    -0.08
     મોટા
    -0.08
     enthousiaste
    -0.08
     böyük
    -0.08
     percor
    -0.08
     grotere
    -0.08
     Spacious
    -0.08
     startups
    -0.08
     تقريب
    -0.08
    POSITIVE LOGITS
     %
    0.10
    %
    0.10
     extracting
    0.10
     &
    0.09
    Extract
    0.09
    ٪
    0.09
    ＆
    0.09
    ％
    0.08
     lowest
    0.08
     `%
    0.08
    Activations Density 0.002%

    No Known Activations