© 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. 25108
    Prev
    Next
    INDEX
    Explanations

    achu

    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
     kete
    -0.09
    rage
    -0.09
     kano
    -0.08
    kos
    -0.08
     bago
    -0.08
     creo
    -0.07
     naughty
    -0.07
     പിട
    -0.07
     прап
    -0.07
    czę
    -0.07
    POSITIVE LOGITS
     significant
    0.08
    植
    0.08
    afi
    0.07
    련
    0.07
    Phones
    0.07
    0.07
    ได้รับ
    0.07
    obs
    0.07
     interrog
    0.07
     circuitry
    0.07
    Activations Density 0.001%
    No Known Activations