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. 12811
    Prev
    Next
    INDEX
    Explanations

    grease

    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
     ingredientes
    -0.07
     Noah
    -0.07
     integrates
    -0.07
    于是
    -0.07
    .embedding
    -0.07
    此同时
    -0.07
     poss
    -0.07
    消
    -0.07
     Respond
    -0.07
    vin
    -0.07
    POSITIVE LOGITS
     Spears
    0.10
    ened
    0.09
    0.09
     Θ
    0.09
    0.08
    �
    0.08
     Γ
    0.08
     Beast
    0.08
    oil
    0.08
     owed
    0.08
    Activations Density 0.004%

    No Known Activations