© 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. 111240
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    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
     midway
    -0.08
     SYN
    -0.08
    .Sample
    -0.07
     Kidd
    -0.07
    CHI
    -0.07
    (proxy
    -0.07
     resurrect
    -0.07
     Magdal
    -0.07
     Nylon
    -0.07
     حاضر
    -0.07
    POSITIVE LOGITS
     vérifier
    0.09
    ě
    0.09
    В
    0.09
    П
    0.08
     vér
    0.08
    ¡
    0.08
    Д
    0.08
    З
    0.08
    ה
    0.08
    Қ
    0.08
    Activations Density 0.128%

    No Known Activations