© 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. 91643
    Prev
    Next
    INDEX
    Explanations

    Space, time, relativity

    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
     strstr
    -0.08
    нув
    -0.08
     Fonts
    -0.08
     Rihanna
    -0.08
     Winner
    -0.08
    渡
    -0.08
     Papa
    -0.07
     |>
    -0.07
     mons
    -0.07
    Flg
    -0.07
    POSITIVE LOGITS
     समय
    0.12
     tempore
    0.12
    .time
    0.12
     时间
    0.12
    時間
    0.12
    Time
    0.12
     time
    0.11
    _TIME
    0.11
     tiempo
    0.11
     время
    0.11
    Activations Density 0.005%

    No Known Activations