© 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. 99249
    Prev
    Next
    INDEX
    Explanations

    1

    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
     burner
    -0.08
     техничес
    -0.07
     alarming
    -0.07
    logen
    -0.07
     HAD
    -0.07
     ут
    -0.07
     прош
    -0.07
    之后
    -0.07
     हुई
    -0.07
     kokoa
    -0.07
    POSITIVE LOGITS
    Adjacent
    0.09
     divisible
    0.09
     ছোট
    0.08
     adjacent
    0.08
     малого
    0.08
     küçük
    0.08
     કહેવ
    0.08
     નાના
    0.08
    鏈
    0.08
     nier
    0.07
    Activations Density 0.036%

    No Known Activations