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. 56249
    Prev
    Next
    INDEX
    Explanations

    be

    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
    .visibility
    -0.10
     ಪಾಲ
    -0.09
    -needed
    -0.08
     conformément
    -0.08
    ",[
    -0.08
     ಗೌ
    -0.08
     любых
    -0.08
     необходимых
    -0.08
     breathable
    -0.08
     respecter
    -0.08
    POSITIVE LOGITS
     excerpt
    0.10
     excerpts
    0.09
    łem
    0.09
    正文
    0.09
     narration
    0.09
    Excerpt
    0.08
    摘
    0.08
     snippet
    0.08
     Additional
    0.08
     narrator
    0.08
    Activations Density 0.056%

    No Known Activations