© 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. 64309
    Prev
    Next
    INDEX
    Explanations

    use

    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
     soient
    -0.08
     vha
    -0.08
    656
    -0.08
     Inflation
    -0.08
    യിലെ
    -0.08
     Zem
    -0.08
     Soil
    -0.08
     urma
    -0.08
     mediation
    -0.08
    ,u
    -0.08
    POSITIVE LOGITS
    ∀
    0.09
     nên
    0.08
     prefers
    0.08
     punctuation
    0.08
    Italic
    0.08
     sarcast
    0.08
     préfère
    0.08
     prefer
    0.08
    Mode
    0.07
    vim
    0.07
    Activations Density 0.002%

    No Known Activations