© 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. 8043
    Prev
    Next
    INDEX
    Explanations

    in

    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
    warnings
    -0.08
    ker
    -0.08
    profil
    -0.08
     ジ
    -0.08
    jd
    -0.08
    신
    -0.08
    ジョ
    -0.07
    veda
    -0.07
     João
    -0.07
     Meine
    -0.07
    POSITIVE LOGITS
     Reihen
    0.10
     alphabetical
    0.10
     symmetrical
    0.09
     порядке
    0.09
    順
    0.09
    顺
    0.09
     क्रम
    0.09
     descending
    0.09
     sequential
    0.09
     ascending
    0.09
    Activations Density 0.027%

    No Known Activations