© 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. 16348
    Prev
    Next
    INDEX
    Explanations

    "how" in other 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
    .....
    -0.08
     democracy
    -0.08
    ****
    -0.08
     fortuna
    -0.08
    idele
    -0.08
     surged
    -0.08
     બની
    -0.08
    //}↵
    -0.08
    ď
    -0.07
    هان
    -0.07
    POSITIVE LOGITS
     how
    0.13
    如何
    0.13
     كيفية
    0.12
     способы
    0.12
     어떻게
    0.12
     如何
    0.12
    在哪里
    0.11
    在哪
    0.11
     bagaimana
    0.11
     qanday
    0.11
    Activations Density 0.032%

    No Known Activations