© 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. 129257
    Prev
    Next
    INDEX
    Explanations

    fractional

    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
     sludge
    -0.08
     gevo
    -0.08
    护
    -0.07
     spar
    -0.07
    summer
    -0.07
     carpet
    -0.07
     ora
    -0.07
    Spam
    -0.07
     nära
    -0.07
    Vrij
    -0.07
    POSITIVE LOGITS
    -turn
    0.08
    -te
    0.08
    юн
    0.08
     yun
    0.07
    -ma
    0.07
     प्रतिशत
    0.07
    division
    0.07
     Prozent
    0.07
    -percent
    0.07
     beautifully
    0.07
    Activations Density 0.006%

    No Known Activations