© 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. 3-RESID-POST-AA
    11. 1398
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ழ
    -0.08
    arms
    -0.08
     регистра
    -0.07
     पर्द
    -0.07
    MD
    -0.07
     LUA
    -0.07
     Shoulder
    -0.07
    hei
    -0.07
     MAC
    -0.07
     സ്
    -0.07
    POSITIVE LOGITS
     Ladies
    0.09
     iff
    0.09
     bgcolor
    0.08
    lier
    0.08
     Confeder
    0.07
     truck
    0.07
    此次
    0.07
     bus
    0.07
     Pepsi
    0.07
     GIS
    0.07
    Activations Density 0.037%

    No Known Activations