© 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. 113334
    Prev
    Next
    INDEX
    Explanations

    soda

    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
     âgées
    -0.08
    elastic
    -0.08
     раньше
    -0.08
    ял
    -0.07
    zyma
    -0.07
     خطوات
    -0.07
     Maths
    -0.07
    -rounded
    -0.07
    أل
    -0.07
    ave
    -0.07
    POSITIVE LOGITS
     této
    0.08
     Clarkson
    0.07
     dieses
    0.07
    unate
    0.07
     potent
    0.07
    MASTER
    0.07
     mistr
    0.07
     moust
    0.07
    WITHOUT
    0.07
     apocalypse
    0.07
    Activations Density 0.000%

    No Known Activations