© 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. 54834
    Prev
    Next
    INDEX
    Explanations

    calculating profit

    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
     voilà
    -0.08
    Ear
    -0.07
    \Common
    -0.07
     yeast
    -0.07
    gard
    -0.07
    JUnit
    -0.07
    Panel
    -0.07
     Zimmerman
    -0.07
     वाला
    -0.07
    SSID
    -0.07
    POSITIVE LOGITS
    米
    0.09
    成本
    0.08
     environs
    0.08
    母
    0.08
     incurs
    0.08
    ải
    0.08
    平均
    0.08
     vergelijking
    0.08
    据
    0.08
     incorporación
    0.07
    Activations Density 0.035%

    No Known Activations