© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51699
    Prev
    Next
    INDEX
    Explanations

    fastening

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compassion
    -0.08
     Kür
    -0.08
     өнг
    -0.08
    ếu
    -0.08
     LEN
    -0.08
     beleid
    -0.08
     stroll
    -0.07
     andamento
    -0.07
     avenida
    -0.07
     phạm
    -0.07
    POSITIVE LOGITS
     befest
    0.32
    固定
    0.31
     secured
    0.30
     securing
    0.29
     attaching
    0.27
     fastening
    0.27
     закреп
    0.27
     attachment
    0.27
     attaches
    0.27
     secure
    0.26
    Activations Density 0.148%

    No Known Activations