© 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. 1309
    Prev
    Next
    INDEX
    Explanations

    import

    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
     invi
    -0.09
     Tint
    -0.08
     midi
    -0.08
     Carn
    -0.08
    Tint
    -0.07
     সম্প্র
    -0.07
    mmat
    -0.07
    ющее
    -0.07
     kerajaan
    -0.07
     Yam
    -0.07
    POSITIVE LOGITS
     promoters
    0.08
    escort
    0.07
     calories
    0.07
     elected
    0.07
     bekommen
    0.07
     policeman
    0.07
    .cls
    0.07
     kinds
    0.07
     આવે
    0.07
     kiddos
    0.07
    Activations Density 0.000%

    No Known Activations