© 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. 11-RESID-POST-AA
    11. 94745
    Prev
    Next
    INDEX
    Explanations

    these/them

    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
     fornece
    -0.08
     slept
    -0.07
     differ
    -0.07
    itic
    -0.07
    ensor
    -0.07
    tim
    -0.07
    雅
    -0.07
     nutric
    -0.07
    abel
    -0.07
     tillegg
    -0.06
    POSITIVE LOGITS
    ქართული
    0.08
     тысячи
    0.08
    khulu
    0.08
     кыргыз
    0.08
     contando
    0.08
     कहानी
    0.08
     кіль
    0.08
     ქართული
    0.08
     داستان
    0.08
     stemmen
    0.08
    Activations Density 0.002%

    No Known Activations