© 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. 15-RESID-POST-AA
    11. 16573
    Prev
    Next
    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zvik
    -0.08
     zvak
    -0.08
     innocence
    -0.08
    Reload
    -0.07
    青春
    -0.07
     swarm
    -0.07
    יניים
    -0.07
     quen
    -0.07
     කිර
    -0.07
     matk
    -0.07
    POSITIVE LOGITS
    ,name
    0.11
    ,title
    0.08
     varchar
    0.08
    Native
    0.08
    	name
    0.08
     duidelijke
    0.08
    	Name
    0.08
    0.08
     Attractive
    0.08
    (name
    0.08
    Activations Density 0.004%

    No Known Activations