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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97591
    Prev
    Next
    INDEX
    Explanations

    Forms of "to be"

    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
     don't
    -0.09
     can
    -0.08
    (G
    -0.07
    ificate
    -0.07
     aren't
    -0.07
     cannot
    -0.07
     নেই
    -0.07
     might
    -0.07
     will
    -0.07
     רוצים
    -0.07
    POSITIVE LOGITS
     être
    0.34
     být
    0.25
     etre
    0.25
    ’être
    0.24
     essere
    0.24
     būti
    0.23
     być
    0.23
     быть
    0.23
     êtres
    0.22
    'être
    0.22
    Activations Density 0.007%

    No Known Activations