© 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. 1516
    Prev
    Next
    INDEX
    Explanations

    Epson

    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
    난
    -0.08
     uche
    -0.08
     gezeigt
    -0.07
    esch
    -0.07
    嬉
    -0.07
     credited
    -0.07
    -labelled
    -0.07
    ناة
    -0.07
     illegally
    -0.07
     comportement
    -0.07
    POSITIVE LOGITS
     Bold
    0.07
     sw
    0.07
     rh
    0.07
    erializer
    0.07
     Multimedia
    0.07
     aft
    0.07
    раг
    0.07
     있도록
    0.07
    sole
    0.06
     내려
    0.06
    Activations Density 0.001%

    No Known Activations