© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25062
    Prev
    Next
    INDEX
    Explanations

    primer

    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
    kte
    -0.08
    akor
    -0.08
     kth
    -0.08
    kele
    -0.08
    न्�
    -0.08
    km
    -0.08
    욱
    -0.07
    文明
    -0.07
     zen
    -0.07
     Torre
    -0.07
    POSITIVE LOGITS
     preparando
    0.09
    护理
    0.08
    Before
    0.07
     bevor
    0.07
     ennen
    0.07
     Performer
    0.07
    IPO
    0.07
    公众号
    0.07
    Blend
    0.07
     înainte
    0.07
    Activations Density 0.003%

    No Known Activations