© 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. 11-RESID-POST-AA
    11. 68274
    Prev
    Next
    INDEX
    Explanations

    math

    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
    .lua
    -0.08
    ンタ
    -0.08
     Hu
    -0.08
    Hu
    -0.08
     particulate
    -0.08
     Luiz
    -0.07
    -0.07
     lily
    -0.07
    Tas
    -0.07
    lu
    -0.07
    POSITIVE LOGITS
    Determine
    0.08
     Públicas
    0.08
     Photograph
    0.08
     выяс
    0.08
     autof
    0.08
     Πρό
    0.08
     вычис
    0.08
    _EXPR
    0.08
     bezüglich
    0.07
    จังหวัด
    0.07
    Activations Density 0.154%
    No Known Activations