© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63594
    Prev
    Next
    INDEX
    Explanations

    magnetism

    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
     massacre
    -0.07
    .promise
    -0.07
    amic
    -0.07
     ritual
    -0.07
     courte
    -0.07
     Gericht
    -0.07
     �
    -0.07
     etiquette
    -0.07
     paginate
    -0.07
    Dos
    -0.07
    POSITIVE LOGITS
    िबार
    0.08
     ఉప
    0.08
    (Constants
    0.07
    інен
    0.07
    ierend
    0.07
    /DC
    0.07
    收益
    0.07
    isaka
    0.07
     అన్ని
    0.07
     Phaser
    0.07
    Activations Density 0.001%

    No Known Activations