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. 43758
    Prev
    Next
    INDEX
    Explanations

    ERA

    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
    lou
    -0.09
    ไม้
    -0.08
     이루
    -0.08
    -0.08
     intox
    -0.08
    ুই
    -0.07
     orchard
    -0.07
    ושים
    -0.07
     flowering
    -0.07
    ושה
    -0.07
    POSITIVE LOGITS
     actuelle
    0.09
    /id
    0.08
     Poco
    0.08
     nightmare
    0.08
    informat
    0.08
    走势
    0.07
     RO
    0.07
     आँ
    0.07
     �
    0.07
    chtend
    0.07
    Activations Density 0.004%

    No Known Activations