© 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. 45290
    Prev
    Next
    INDEX
    Explanations

    press

    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
     acc
    -0.08
     address
    -0.08
     ego
    -0.08
     ప్రభుత్వం
    -0.08
     design
    -0.07
     SIZE
    -0.07
     Mario
    -0.07
     synthetic
    -0.07
     зел
    -0.07
     Synthetic
    -0.07
    POSITIVE LOGITS
     wells
    0.09
     brukes
    0.09
    指南
    0.08
    Dropbox
    0.08
     njegov
    0.08
    Writes
    0.07
    Usage
    0.07
    �
    0.07
    classpath
    0.07
     wandel
    0.07
    Activations Density 0.001%

    No Known Activations