© 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. 30117
    Prev
    Next
    INDEX
    Explanations

    complex numbers

    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
    .methods
    -0.08
    ["
    -0.07
    ಿಮೆ
    -0.07
    .vaadin
    -0.07
      ↵  ↵
    -0.07
     fires
    -0.07
     methods
    -0.07
    .at
    -0.07
     methodologies
    -0.07
    .demo
    -0.07
    POSITIVE LOGITS
     Vai
    0.08
     Beaut
    0.08
    cpf
    0.08
    Vai
    0.08
     soh
    0.08
     افزود
    0.08
     Germ
    0.08
    中过
    0.07
     cpf
    0.07
     Σ
    0.07
    Activations Density 0.024%

    No Known Activations