© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64774
    Prev
    Next
    INDEX
    Explanations

    day shipping

    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
    zić
    -0.08
    _Def
    -0.08
    iante
    -0.07
     Reid
    -0.07
     Rex
    -0.07
     Winnie
    -0.07
     tano
    -0.07
    воноч
    -0.07
    Behavior
    -0.07
    орган
    -0.07
    POSITIVE LOGITS
     chóng
    0.09
     rápida
    0.09
     സേവ
    0.09
     entrega
    0.09
    -registration
    0.08
     schnelle
    0.08
    silver
    0.08
    -ish
    0.08
    /location
    0.08
    配送
    0.08
    Activations Density 0.034%

    No Known Activations