© 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. 44534
    Prev
    Next
    INDEX
    Explanations

    cooperative

    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
     ומ
    -0.08
    680
    -0.08
    ушы
    -0.08
    .ve
    -0.08
     assault
    -0.08
    חת
    -0.07
    pute
    -0.07
    (V
    -0.07
     Pest
    -0.07
     Vé
    -0.07
    POSITIVE LOGITS
     phenomenon
    0.12
     phenomena
    0.12
     phénomène
    0.11
     fenô
    0.10
     fenómeno
    0.09
     fenomen
    0.08
     samman
    0.08
     حدث
    0.08
     randomness
    0.08
     klin
    0.08
    Activations Density 0.008%

    No Known Activations