© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    يا

    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
     dese
    -0.08
     fus
    -0.08
    ிறார்
    -0.07
    ната
    -0.07
    /activity
    -0.07
    Browse
    -0.07
     الشب
    -0.07
    еті
    -0.07
     verble
    -0.07
    وری
    -0.07
    POSITIVE LOGITS
     Pow
    0.08
    oku
    0.07
    iseaux
    0.07
     cà
    0.07
     Maur
    0.07
     John's
    0.07
    hv
    0.07
     Café
    0.07
     Mord
    0.07
     Bord
    0.07
    Activations Density 0.006%

    No Known Activations