© 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. 95438
    Prev
    Next
    INDEX
    Explanations

    )

    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
    ceil
    -0.08
    xes
    -0.07
     deng
    -0.07
    却
    -0.07
     sump
    -0.07
    (Y
    -0.07
    筋
    -0.07
    elay
    -0.07
    �
    -0.07
     కూడ
    -0.07
    POSITIVE LOGITS
     hy
    0.08
     Hy
    0.07
     Ron
    0.07
     mith
    0.07
    of
    0.07
     publish
    0.07
     ling
    0.07
     hippoc
    0.07
     dưới
    0.07
     primo
    0.07
    Activations Density 0.068%

    No Known Activations