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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 91113
    Prev
    Next
    INDEX
    Explanations

    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
     slowed
    -0.08
     stall
    -0.08
     paused
    -0.08
     blockage
    -0.08
     Layer
    -0.07
     scrub
    -0.07
     Completable
    -0.07
     interrupted
    -0.07
     Securities
    -0.07
     feels
    -0.07
    POSITIVE LOGITS
    Im
    0.09
     Im
    0.08
    待遇
    0.08
    âte
    0.08
    使命
    0.08
     Hint
    0.08
    bbbb
    0.08
    Herm
    0.07
    
    0.07
    函数
    0.07
    Activations Density 0.001%

    No Known Activations