© 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. 19-RESID-POST-AA
    6. 102496
    Prev
    Next
    INDEX
    Explanations

    variations of "being" or "called"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eins
    -0.08
    ઉ
    -0.08
     barcos
    -0.07
    -hours
    -0.07
    -input
    -0.07
    ucks
    -0.07
     HOURS
    -0.07
     Tenemos
    -0.07
    ર્જ
    -0.07
    ર્ત
    -0.07
    POSITIVE LOGITS
     termed
    0.16
     being
    0.16
    being
    0.15
     pagiging
    0.15
    Being
    0.14
     Being
    0.14
    作为
    0.14
     явля
    0.13
     called
    0.13
    是一
    0.13
    Activations Density 0.198%

    No Known Activations