© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5921
    Prev
    Next
    INDEX
    Explanations

    Arabic words

    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
     Стар
    -0.07
     stru
    -0.07
    Bron
    -0.07
     Нес
    -0.07
    ublik
    -0.07
    uneet
    -0.07
     činjen
    -0.06
    grat
    -0.06
     ekolog
    -0.06
     органов
    -0.06
    POSITIVE LOGITS
    ارات
    0.18
    ارة
    0.14
    ਾਰ
    0.13
    ام
    0.12
    ارتی
    0.11
    ارية
    0.10
    ાર
    0.10
    ારો
    0.10
    ार
    0.10
     nghiệ
    0.10
    Activations Density 0.001%

    No Known Activations