© 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. 108174
    Prev
    Next
    INDEX
    Explanations

    Model

    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
    ancia
    -0.08
     assassin
    -0.08
     hai
    -0.08
     assass
    -0.08
     dañ
    -0.08
     translates
    -0.08
    atores
    -0.07
     simplesmente
    -0.07
     ite
    -0.07
     moneda
    -0.07
    POSITIVE LOGITS
    tabl
    0.08
    alone
    0.07
    fullname
    0.07
     taught
    0.07
    icelo
    0.07
    Lic
    0.07
    featured
    0.07
    enabled
    0.07
    Declar
    0.07
     प्रण
    0.07
    Activations Density 0.073%

    No Known Activations