© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    may

    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
    াস্থ্য
    -0.08
    -প
    -0.08
    -na
    -0.07
    তে
    -0.07
    ার
    -0.07
     examines
    -0.07
     மக்கள்
    -0.07
    %A
    -0.07
    curité
    -0.07
     تدو
    -0.07
    POSITIVE LOGITS
     Tudor
    0.07
     Cove
    0.07
     cif
    0.07
    皇家
    0.07
     attenuation
    0.07
     Choices
    0.07
     naughty
    0.07
     choc
    0.07
     Karin
    0.07
     Contin
    0.07
    Activations Density 0.000%

    No Known Activations