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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 112682
    Prev
    Next
    INDEX
    Explanations

    chew

    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
     precipit
    -0.09
    .Height
    -0.09
     volte
    -0.08
     perfekt
    -0.08
     orchestra
    -0.07
     ej
    -0.07
     낮
    -0.07
    272
    -0.07
     ол
    -0.07
    iscus
    -0.07
    POSITIVE LOGITS
    🏼
    0.10
    🏻
    0.09
    iness
    0.08
     Hur
    0.08
     chewing
    0.08
    KL
    0.08
    hin
    0.08
     Dent
    0.07
     Kamp
    0.07
    bone
    0.07
    Activations Density 0.003%

    No Known Activations