© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 13002
    Prev
    Next
    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    green
    -0.08
    GREEN
    -0.07
    _green
    -0.07
     polyethylene
    -0.07
     Pelle
    -0.07
    	Is
    -0.07
    _nan
    -0.07
     closest
    -0.07
     GREEN
    -0.07
     Or
    -0.07
    POSITIVE LOGITS
     hey
    0.08
     Sql
    0.08
     heil
    0.08
     feeds
    0.08
    Feeds
    0.08
     Acrobat
    0.08
    .attach
    0.08
     Attached
    0.07
    úd
    0.07
     తర
    0.07
    Activations Density 0.001%

    No Known Activations