© 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. 68234
    Prev
    Next
    INDEX
    Explanations

    want

    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
     Kunst
    -0.09
     개선
    -0.08
    wijf
    -0.08
     सुधार
    -0.08
     Хар
    -0.08
     Cpu
    -0.08
    ngr
    -0.08
     mh
    -0.07
     Etter
    -0.07
    bots
    -0.07
    POSITIVE LOGITS
    ading
    0.07
    ADING
    0.07
     monoch
    0.07
     contribut
    0.07
     MON
    0.07
    dddd
    0.07
     measuring
    0.07
     propag
    0.07
    quan
    0.07
     courtyard
    0.07
    Activations Density 0.002%

    No Known Activations