© 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. 44768
    Prev
    Next
    INDEX
    Explanations

    thesis

    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
     GI
    -0.08
     ISO
    -0.08
     machinery
    -0.08
     MIME
    -0.08
     SPI
    -0.08
     LG
    -0.07
     эксп
    -0.07
     normalize
    -0.07
     SA
    -0.07
     procedure
    -0.07
    POSITIVE LOGITS
     statement
    0.10
     विधान
    0.10
     वक्त
    0.09
    phr
    0.09
    一句
    0.09
     Statement
    0.09
    statement
    0.09
     Thesis
    0.09
     annonc
    0.09
    _statement
    0.09
    Activations Density 0.004%

    No Known Activations