© 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. 108709
    Prev
    Next
    INDEX
    Explanations

    Parent context

    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
     Structural
    -0.08
     Александ
    -0.08
     Genes
    -0.08
     suiv
    -0.08
    	Status
    -0.07
     പ്രശ
    -0.07
     문제가
    -0.07
    闻
    -0.07
     stumbling
    -0.07
     Garner
    -0.07
    POSITIVE LOGITS
     allotted
    0.10
     width
    0.10
     контей
    0.10
    いっぱい
    0.09
     viewport
    0.09
     margins
    0.09
    /container
    0.09
    容
    0.09
    container
    0.09
    屏
    0.09
    Activations Density 0.006%

    No Known Activations