© 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. 47811
    Prev
    Next
    INDEX
    Explanations

    internal and external

    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
    کتا
    -0.08
    ंध
    -0.07
     cuanto
    -0.07
     kezd
    -0.07
    AS
    -0.07
     pronto
    -0.07
    ording
    -0.07
     antiqu
    -0.07
    აღ
    -0.07
    ordnung
    -0.07
    POSITIVE LOGITS
     الداخلي
    0.18
     внутрен
    0.18
    ternal
    0.17
     الداخلية
    0.17
    /internal
    0.17
     extérieure
    0.17
     notran
    0.17
    内
    0.17
     наруж
    0.16
    内部
    0.16
    Activations Density 0.116%

    No Known Activations