© 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. 108640
    Prev
    Next
    INDEX
    Explanations

    path, entry

    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
     ਏ
    -0.08
    faz
    -0.08
     Load
    -0.08
     ตาราง
    -0.07
    ਏ
    -0.07
     belast
    -0.07
    ောင်
    -0.07
     yük
    -0.07
     hemorr
    -0.07
    zum
    -0.07
    POSITIVE LOGITS
     concat
    0.08
     dataset
    0.08
     strands
    0.08
     лишь
    0.08
     acknowledges
    0.08
     gust
    0.08
     archived
    0.08
    ан
    0.08
    .orders
    0.08
     conson
    0.07
    Activations Density 0.000%

    No Known Activations