© 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. 614
    Prev
    Next
    INDEX
    Explanations

    sky

    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
     dimension
    -0.08
     Van
    -0.07
    Entre
    -0.07
    Volumes
    -0.07
    _dimension
    -0.07
    Dimension
    -0.07
     Hazard
    -0.07
     volumes
    -0.07
     Barr
    -0.07
    Barr
    -0.07
    POSITIVE LOGITS
    ，高
    0.09
     relentless
    0.09
     Regal
    0.08
    白浆
    0.08
     ishlab
    0.08
     edificios
    0.08
     relentlessly
    0.08
    全天
    0.08
    、高
    0.08
    0.08
    Activations Density 0.004%
    No Known Activations