© 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. 96627
    Prev
    Next
    INDEX
    Explanations

    mistyped or miswritten equations

    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
     mejoras
    -0.09
     netjes
    -0.09
    不卡
    -0.09
    不限
    -0.09
     თითო
    -0.08
    不会
    -0.08
     disputed
    -0.08
     aghaidh
    -0.08
     gach
    -0.08
     modificaciones
    -0.08
    POSITIVE LOGITS
     due
    0.15
    ;
    0.14
    —it
    0.14
    due
    0.13
    Due
    0.13
    —they
    0.12
     بسبب
    0.12
    —the
    0.12
     causing
    0.12
    —we
    0.11
    Activations Density 0.054%

    No Known Activations