© 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. 112611
    Prev
    Next
    INDEX
    Explanations

    words

    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
     uwa
    -0.08
    дет
    -0.08
    }")]↵
    -0.08
     Ukraine
    -0.07
    )}</
    -0.07
     adop
    -0.07
     Есть
    -0.07
     রয়েছে
    -0.07
     vid
    -0.07
     unconscious
    -0.07
    POSITIVE LOGITS
    Xpath
    0.08
     recursively
    0.08
    覆
    0.07
     paragraphs
    0.07
     wrest
    0.07
    Xpaths
    0.07
    ANDS
    0.07
     అధ్య
    0.07
     capítulos
    0.07
    tolist
    0.07
    Activations Density 0.000%

    No Known Activations