© 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. 26413
    Prev
    Next
    INDEX
    Explanations

    Code initializing coordinates

    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
     dosage
    -0.08
    proj
    -0.08
     dose
    -0.07
     displacement
    -0.07
     chá
    -0.07
    ครงการ
    -0.07
     verre
    -0.07
     translation
    -0.07
    .ps
    -0.07
     trivial
    -0.07
    POSITIVE LOGITS
     중
    0.09
    .yellow
    0.09
     hierfür
    0.08
    .good
    0.08
     Inject
    0.08
     populares
    0.08
     Injection
    0.08
     Vorsch
    0.08
     Gelder
    0.08
     Gegend
    0.08
    Activations Density 0.002%

    No Known Activations