© 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. 103333
    Prev
    Next
    INDEX
    Explanations

    periods

    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
     Routed
    -0.09
     routed
    -0.09
    (case
    -0.08
    .fxml
    -0.08
     વિવિધ
    -0.08
     다양한
    -0.08
    ancée
    -0.08
    ([...
    -0.08
     Sug
    -0.08
    .list
    -0.08
    POSITIVE LOGITS
     periods
    0.13
    多少期
    0.11
    Periods
    0.11
     périodes
    0.11
     períodos
    0.11
     období
    0.10
    期間
    0.10
    期期
    0.10
    _PERIOD
    0.10
    _period
    0.10
    Activations Density 0.006%

    No Known Activations