Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130491
    Prev
    Next
    INDEX
    Explanations

    arrow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afili
    -0.08
    িগত
    -0.07
    法人
    -0.07
     Pablo
    -0.07
     Eld
    -0.07
    initions
    -0.07
    union
    -0.07
     العربية
    -0.07
    _encoding
    -0.07
    077
    -0.07
    POSITIVE LOGITS
    ಳಿ
    0.08
     표시
    0.08
     Pencil
    0.07
     Feather
    0.07
    势
    0.07
    -eyed
    0.07
    tren
    0.07
     buat
    0.07
    ↵
    ↵
    ↵
    ↵
    0.07
     Metall
    0.07
    Activations Density 0.002%

    No Known Activations