© 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. 30253
    Prev
    Next
    INDEX
    Explanations

    electromagnetic radiation

    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
    look
    -0.08
     clutch
    -0.08
    Winner
    -0.08
    /account
    -0.08
    Duplic
    -0.07
    -0.07
    MODEL
    -0.07
    winner
    -0.07
    úa
    -0.07
    Undo
    -0.07
    POSITIVE LOGITS
     wavelengths
    0.16
     wavelength
    0.14
     radiation
    0.13
     rays
    0.12
     ultraviolet
    0.12
     photons
    0.12
     infrared
    0.11
     spectrum
    0.10
     radio
    0.10
     spectroscopy
    0.10
    Activations Density 0.012%
    No Known Activations