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. 43137
    Prev
    Next
    INDEX
    Explanations

    global world

    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
    那些
    -0.08
    章节
    -0.08
     llamados
    -0.08
    -0.08
     Kuk
    -0.07
    mia
    -0.07
    故事
    -0.07
    �
    -0.07
     worlds
    -0.07
     copper
    -0.07
    POSITIVE LOGITS
    -wide
    0.15
     entière
    0.10
    -scale
    0.10
     మొత్త
    0.09
     encompassing
    0.09
    -reaching
    0.09
     totalité
    0.09
    weite
    0.09
     encomp
    0.09
     تقريب
    0.08
    Activations Density 0.029%

    No Known Activations