© 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. 113198
    Prev
    Next
    INDEX
    Explanations

    rightarrow

    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
     لطف
    -0.08
     homic
    -0.08
    otch
    -0.08
    iddi
    -0.08
     Hér
    -0.08
     význam
    -0.07
    热点
    -0.07
     Hannah
    -0.07
    ுதல்
    -0.07
    发挥
    -0.07
    POSITIVE LOGITS
    Fluid
    0.07
     Fluid
    0.07
    -fluid
    0.07
    (skill
    0.07
    เรียน
    0.07
    .skill
    0.07
     cave
    0.07
     fluid
    0.07
     plein
    0.07
     প্রদ
    0.07
    Activations Density 0.006%

    No Known Activations