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. 11-RESID-POST-AA
    6. 48975
    Prev
    Next
    INDEX
    Explanations

    forgiveness

    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
    (False
    -0.09
    Concurrency
    -0.09
     enthousiaste
    -0.08
    Density
    -0.08
    _io
    -0.08
     yoğun
    -0.08
     enthousiasme
    -0.08
    (run
    -0.07
    _kwargs
    -0.07
    倍率
    -0.07
    POSITIVE LOGITS
     forgiveness
    0.13
     التخلص
    0.12
     избавиться
    0.11
     очищ
    0.11
     trauma
    0.11
     избав
    0.11
     освоб
    0.11
     repentance
    0.10
     healing
    0.10
     rehabilitation
    0.10
    Activations Density 0.039%

    No Known Activations