© 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. 660
    Prev
    Next
    INDEX
    Explanations

    many

    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
     یعنی
    -0.09
     unequiv
    -0.08
     తర
    -0.08
    yos
    -0.08
     №
    -0.08
     coba
    -0.08
     Transportation
    -0.08
     yönt
    -0.08
     Damp
    -0.08
    -u
    -0.08
    POSITIVE LOGITS
     మంది
    0.12
    ๆ
    0.09
    -lasting
    0.09
    365
    0.08
     voorkomende
    0.08
    দিন
    0.08
    Sky
    0.08
     vantage
    0.08
     hits
    0.08
    มาย
    0.08
    Activations Density 0.065%

    No Known Activations