© 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. 19-RESID-POST-AA
    11. 103098
    Prev
    Next
    INDEX
    Explanations

    ordered

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minster
    -0.08
    ceis
    -0.08
     limpia
    -0.08
    Weekend
    -0.08
     chung
    -0.08
    简
    -0.08
    简介
    -0.08
     inconn
    -0.08
     limpa
    -0.08
     cuma
    -0.08
    POSITIVE LOGITS
     ordered
    0.16
    ordered
    0.15
     distinguish
    0.15
    Ordered
    0.14
     directional
    0.14
     ORDER
    0.14
     Ordered
    0.13
     distinctions
    0.13
     distinguishes
    0.13
     distin
    0.13
    Activations Density 0.050%

    No Known Activations