© 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. 94756
    Prev
    Next
    INDEX
    Explanations

    Roman numerals and structured formats

    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
     bulletin
    -0.09
    сер
    -0.08
    gray
    -0.07
     arab
    -0.07
    guei
    -0.07
    SCR
    -0.07
     expend
    -0.07
    fficients
    -0.07
    cei
    -0.07
    chè
    -0.07
    POSITIVE LOGITS
    0.10
     год
    0.08
     {(
    0.08
     alene
    0.07
    ит
    0.07
     [(
    0.07
     пород
    0.07
     containment
    0.07
    �
    0.07
    ül
    0.07
    Activations Density 0.003%

    No Known Activations