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

    Neuronpedia

    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. 78143
    Prev
    Next
    INDEX
    Explanations

    izing

    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
    Ј
    -0.08
    丝
    -0.08
    Fore
    -0.08
    **/↵↵
    -0.08
    је
    -0.08
    јед
    -0.07
    >tagger
    -0.07
    ingen
    -0.07
    984
    -0.07
    uebles
    -0.07
    POSITIVE LOGITS
     ziz
    0.08
     passionate
    0.08
     zim
    0.08
     accuse
    0.07
     sé
    0.07
     gez
    0.07
    oria
    0.07
    uited
    0.07
     مناسب
    0.07
     لاز
    0.07
    Activations Density 0.000%

    No Known Activations