© 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. 19-RESID-POST-AA
    11. 103247
    Prev
    Next
    INDEX
    Explanations

    say "ed"

    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
    уйста
    -0.11
     itu
    -0.10
    ITIES
    -0.10
    즘
    -0.10
    keiten
    -0.09
    ότητες
    -0.09
    uksia
    -0.09
    કા
    -0.09
    こと
    -0.09
     경우
    -0.09
    POSITIVE LOGITS
    ed
    0.63
    ED
    0.32
    edka
    0.31
    edf
    0.30
    edal
    0.27
    edly
    0.27
    edwe
    0.26
    েড
    0.26
    edik
    0.25
    enticated
    0.25
    Activations Density 0.186%

    No Known Activations