© 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. 25968
    Prev
    Next
    INDEX
    Explanations

    Friday

    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
     bilen
    -0.08
    -pers
    -0.08
     molecule
    -0.08
     original
    -0.07
     nucleus
    -0.07
    аря
    -0.07
    keletal
    -0.07
     criatura
    -0.07
    Challenge
    -0.07
    pull
    -0.07
    POSITIVE LOGITS
    皆
    0.08
     Antibi
    0.07
    BUT
    0.07
     antibiotics
    0.07
    嬉
    0.07
    、有
    0.07
    avna
    0.07
    /on
    0.07
     viscos
    0.07
    ults
    0.07
    Activations Density 0.008%

    No Known Activations