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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 119276
    Prev
    Next
    INDEX
    Explanations

    on

    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
    _fr
    -0.07
    เหน
    -0.07
     sign
    -0.07
     vibe
    -0.07
     frig
    -0.07
    -0.07
    ter
    -0.07
     ร
    -0.07
    `.↵
    -0.07
    ไว้
    -0.07
    POSITIVE LOGITS
    .VERSION
    0.09
     systematically
    0.09
     saý
    0.08
     progressively
    0.08
     childbirth
    0.08
     حج
    0.08
     სც
    0.08
    дрийн
    0.08
    ിപ്രായ
    0.08
    ENGTH
    0.08
    Activations Density 0.005%

    No Known Activations