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. 19531
    Prev
    Next
    INDEX
    Explanations

    Storage capacity

    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
     воздейств
    -0.08
     веществ
    -0.08
    rown
    -0.08
     resembling
    -0.08
     suav
    -0.08
    apy
    -0.08
    iddy
    -0.08
     loosen
    -0.08
     indebted
    -0.08
     سرگر
    -0.07
    POSITIVE LOGITS
    容量
    0.18
     sizes
    0.12
    サイズ
    0.12
     ظرفیت
    0.11
     حجم
    0.11
     Capacity
    0.11
     SSD
    0.11
    Capacity
    0.11
     almacenamiento
    0.11
     stockage
    0.11
    Activations Density 0.015%

    No Known Activations