Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19555
    Prev
    Next
    INDEX
    Explanations

    resilience

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _MOUSE
    -0.09
     CCTV
    -0.09
     Adviser
    -0.08
     románt
    -0.08
     המז
    -0.08
     parked
    -0.08
    Erot
    -0.08
    偷窥
    -0.08
     pleasurable
    -0.08
     stereo
    -0.08
    POSITIVE LOGITS
     resilience
    0.31
     resilient
    0.26
     perseverance
    0.24
     resil
    0.24
     toughness
    0.18
     courage
    0.18
    坚
    0.18
     withstand
    0.17
    毅
    0.17
    勇
    0.17
    Activations Density 0.134%

    No Known Activations