© 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. 7-RESID-POST-AA
    11. 1381
    Prev
    Next
    INDEX
    Explanations

    cos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gran
    -0.08
    Gran
    -0.08
    شى
    -0.08
     Sony
    -0.08
    Sony
    -0.08
     broadband
    -0.08
    شی
    -0.07
    Variation
    -0.07
     advisory
    -0.07
     Gran
    -0.07
    POSITIVE LOGITS
     ersch
    0.09
    _DOUBLE
    0.08
    ijzen
    0.08
    ission
    0.08
     Cra
    0.08
    裂
    0.08
     пот
    0.08
     diamant
    0.08
    laşdır
    0.08
     денежных
    0.07
    Activations Density 0.003%

    No Known Activations