© 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. 30939
    Prev
    Next
    INDEX
    Explanations

    Personal stories/epiphanies

    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
     Bucc
    -0.08
    ুদ
    -0.08
     cosplay
    -0.08
    ysters
    -0.08
     jerseys
    -0.07
    қы
    -0.07
     stockings
    -0.07
    MATCH
    -0.07
     byr
    -0.07
    бір
    -0.07
    POSITIVE LOGITS
     Erkennt
    0.12
    发现
    0.12
    认识
    0.12
    悟
    0.10
     recognizing
    0.10
     revelations
    0.10
     revelation
    0.10
     discoveries
    0.10
     발견
    0.09
     discovered
    0.09
    Activations Density 0.040%

    No Known Activations