© 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. 18887
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     iets
    -0.08
     auch
    -0.07
     arī
    -0.07
    yanye
    -0.07
    gyny
    -0.07
     etiam
    -0.07
     någon
    -0.07
    גם
    -0.07
    Auch
    -0.07
     сих
    -0.07
    POSITIVE LOGITS
     unless
    0.31
    unless
    0.29
     Unless
    0.28
    Unless
    0.27
     tenzij
    0.25
     generally
    0.23
     rarely
    0.22
     Generally
    0.22
     generalmente
    0.21
    Generally
    0.21
    Activations Density 0.117%

    No Known Activations