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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119151
    Prev
    Next
    INDEX
    Explanations

    General text

    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
    이번
    -0.08
    ,total
    -0.08
     entirety
    -0.07
    에서도
    -0.07
     kdy
    -0.07
    \Command
    -0.07
     sogar
    -0.07
    ุน
    -0.07
    -0.07
     spelen
    -0.07
    POSITIVE LOGITS
    后来
    0.08
     privat
    0.08
     λόγω
    0.08
     പിന്നീട്
    0.08
     يعود
    0.08
    Migr
    0.08
    Migration
    0.08
     Ende
    0.08
    OOM
    0.08
    ðið
    0.08
    Activations Density 0.171%

    No Known Activations