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. 11718
    Prev
    Next
    INDEX
    Explanations

    merge

    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
     ira
    -0.08
    惯
    -0.08
    illaume
    -0.07
    乙
    -0.07
    iot
    -0.07
     accessory
    -0.07
     crud
    -0.07
     �
    -0.07
    ibonacci
    -0.07
    열
    -0.07
    POSITIVE LOGITS
    _into
    0.11
    .merge
    0.10
    Into
    0.09
     mergers
    0.08
     Alex
    0.07
     souls
    0.07
     garder
    0.07
    owing
    0.07
    edt
    0.07
     recession
    0.07
    Activations Density 0.006%

    No Known Activations