© 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. 102460
    Prev
    Next
    INDEX
    Explanations

    Non-English numbers

    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
     four
    -0.11
     Four
    -0.11
     ચાર
    -0.11
    _four
    -0.10
    前三
    -0.10
     ನಾಲ
    -0.10
     चार
    -0.10
     quatrième
    -0.10
    four
    -0.10
     أربعة
    -0.10
    POSITIVE LOGITS
    １１
    0.11
     zwölf
    0.11
     చివ
    0.11
    ９
    0.11
    ১১
    0.11
     শেষে
    0.10
    ۹
    0.10
    最後
    0.10
    ৯
    0.10
    ११
    0.10
    Activations Density 0.011%

    No Known Activations