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. 130249
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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
     പരിപാട
    -0.08
     അവതരിപ്പ
    -0.08
     Управ
    -0.08
     conceived
    -0.08
     сегодня
    -0.07
     Senioren
    -0.07
     валют
    -0.07
     endowed
    -0.07
     sustainable
    -0.07
     sustained
    -0.07
    POSITIVE LOGITS
     grep
    0.16
    grep
    0.13
     searched
    0.12
    Searching
    0.11
     searching
    0.11
    Search
    0.11
    -search
    0.11
     搜
    0.11
     searchable
    0.11
     fichiers
    0.11
    Activations Density 0.010%

    No Known Activations