© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24572
    Prev
    Next
    INDEX
    Explanations

    vacuum cleaners

    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
     paternal
    -0.09
    ,new
    -0.08
     suplement
    -0.08
     adequate
    -0.08
     દેખ
    -0.08
     overdue
    -0.07
     سے
    -0.07
     proactive
    -0.07
     isnt
    -0.07
    ijom
    -0.07
    POSITIVE LOGITS
    haus
    0.09
    输出
    0.09
    鼓
    0.08
    洞
    0.07
    _output
    0.07
     gerçek
    0.07
     Intern
    0.07
    输入
    0.07
    ts
    0.07
     输出
    0.07
    Activations Density 0.006%

    No Known Activations