© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47425
    Prev
    Next
    INDEX
    Explanations

    divide

    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
     '('
    -0.07
    Flex
    -0.07
    Hello
    -0.07
    ))
    -0.07
     deque
    -0.07
     agradável
    -0.07
     खू
    -0.07
    膽
    -0.07
     secretion
    -0.07
     शव
    -0.07
    POSITIVE LOGITS
     literacy
    0.12
     connectivity
    0.11
     internetu
    0.10
     broadband
    0.10
     rural
    0.10
     Literacy
    0.10
     Broadband
    0.10
    .educ
    0.10
     wireless
    0.09
     bandwidth
    0.09
    Activations Density 0.018%

    No Known Activations