© 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. 19-RESID-POST-AA
    11. 103536
    Prev
    Next
    INDEX
    Explanations

    Down arrow symbol

    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
    ()},
    -0.10
    ുകളിൽ
    -0.10
    ()}</
    -0.09
    ially
    -0.09
     אבל
    -0.09
    וכל
    -0.09
    the
    -0.09
    atuurlijk
    -0.09
    ']>;↵
    -0.09
    !).↵↵
    -0.09
    POSITIVE LOGITS
    🏻
    0.14
    🏼
    0.13
    ︎
    0.13
    ↓↓
    0.12
    ▼
    0.12
    0.11
    ────
    0.11
    0.11
    0.11
    0.11
    Activations Density 0.001%

    No Known Activations