© 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 EvalsExportsinterp-engineNEWAPI 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. 71064
    Prev
    Next
    INDEX
    Explanations

    not

    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
     waarde
    -0.08
     Werden
    -0.08
     യോഗ
    -0.08
     yog
    -0.08
    ెన్
    -0.08
    wake
    -0.08
    werden
    -0.07
    വർ
    -0.07
     Richmond
    -0.07
     stereotyp
    -0.07
    POSITIVE LOGITS
     아니라
    0.08
     otherwise
    0.08
    ager
    0.08
     invés
    0.08
     નહીં
    0.08
    rather
    0.07
    ुक
    0.07
     necessarily
    0.07
    ifice
    0.07
    ANI
    0.07
    Activations Density 0.031%

    No Known Activations