© 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. 95418
    Prev
    Next
    INDEX
    Explanations

    bed

    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
     bele
    -0.09
     keeps
    -0.08
     quasi
    -0.07
     bisher
    -0.07
     zukünft
    -0.07
     resurrect
    -0.07
     breadth
    -0.07
     Besch
    -0.07
     beast
    -0.07
    गर
    -0.07
    POSITIVE LOGITS
    桑
    0.09
     oatmeal
    0.08
    用品
    0.08
     ಇರುವ
    0.08
     metabol
    0.08
     Palavra
    0.07
    (after
    0.07
    .erp
    0.07
    期限
    0.07
    lle
    0.07
    Activations Density 0.004%

    No Known Activations