© 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. 102324
    Prev
    Next
    INDEX
    Explanations

    Instrument

    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
    ינט
    -0.08
     Íslandi
    -0.08
    inshi
    -0.08
    يمكن
    -0.07
    integer
    -0.07
    دين
    -0.07
     industrie
    -0.07
     інш
    -0.07
     yanzu
    -0.07
    年的
    -0.07
    POSITIVE LOGITS
    -магаз
    0.12
    σως
    0.12
    ತ್ತೀಚ
    0.12
    /ioutil
    0.11
    uitive
    0.11
    roduction
    0.11
    ividual
    0.11
    ERRUP
    0.11
    ognito
    0.11
    itialize
    0.11
    Activations Density 0.803%

    No Known Activations