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. 58417
    Prev
    Next
    INDEX
    Explanations

    XML code related

    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
     sara
    -0.08
     tind
    -0.07
    _bytes
    -0.07
     addedge
    -0.07
    Bytes
    -0.07
    Ptrs
    -0.07
    Her
    -0.07
    655
    -0.07
    tit
    -0.07
     tit
    -0.07
    POSITIVE LOGITS
    leton
    0.10
    haften
    0.08
    _TEMPLATE
    0.08
    模板
    0.08
    _USER
    0.08
     interiores
    0.08
    _User
    0.08
     TEMPLATE
    0.08
    śred
    0.08
     الوحدة
    0.08
    Activations Density 0.003%

    No Known Activations