© 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. 15-RESID-POST-AA
    11. 16619
    Prev
    Next
    INDEX
    Explanations

    "all" in different languages

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     andere
    -0.08
    /dev
    -0.08
    esom
    -0.08
     Other
    -0.08
     altres
    -0.08
    رخ
    -0.08
     other
    -0.08
    其他
    -0.08
     autres
    -0.08
     ued
    -0.08
    POSITIVE LOGITS
     semuanya
    0.12
     அனைத்து
    0.11
     كل
    0.10
     wszyst
    0.10
     ಎಲ್ಲಾ
    0.10
     அனை
    0.10
     semua
    0.10
     setiap
    0.10
     எல்ல
    0.10
     kaikke
    0.10
    Activations Density 0.011%

    No Known Activations