© 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. 23-RESID-POST-AA
    11. 49373
    Prev
    Next
    INDEX
    Explanations

    신

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coa
    -0.08
    ра
    -0.07
    宠
    -0.07
    _KERNEL
    -0.07
     Signing
    -0.07
     Сп
    -0.07
    terra
    -0.07
    يته
    -0.07
    agé
    -0.07
    平县
    -0.07
    POSITIVE LOGITS
    ött
    0.08
    Assess
    0.08
    림
    0.08
    েবা
    0.08
     Jackson
    0.08
    দের
    0.08
    July
    0.08
    াদের
    0.08
     laten
    0.08
    duck
    0.08
    Activations Density 0.001%

    No Known Activations