© 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. 99662
    Prev
    Next
    INDEX
    Explanations

    cosmology

    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
     battery
    -0.09
     Battery
    -0.09
     soldats
    -0.08
     ibi
    -0.08
     Tantra
    -0.08
     Fence
    -0.08
     Kindle
    -0.08
     muur
    -0.08
    _ble
    -0.08
     Aron
    -0.08
    POSITIVE LOGITS
     competed
    0.09
    Balances
    0.08
    stackpath
    0.08
     balances
    0.08
     ગ્રામ
    0.08
    balances
    0.08
    Computed
    0.08
    Gameplay
    0.08
     primordial
    0.08
     પ્લ
    0.08
    Activations Density 0.002%

    No Known Activations