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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12934
    Prev
    Next
    INDEX
    Explanations

    moving

    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
    gmail
    -0.09
    पाल
    -0.08
     Quest
    -0.08
    Gateway
    -0.08
     Verständ
    -0.08
     Pflicht
    -0.07
    Destino
    -0.07
    gateway
    -0.07
    Destination
    -0.07
     สำหรับ
    -0.07
    POSITIVE LOGITS
     pauses
    0.12
     uninterrupted
    0.11
     paused
    0.11
    忙
    0.11
     активности
    0.11
    闲
    0.11
    状态
    0.10
    -active
    0.10
    paused
    0.10
    Paused
    0.10
    Activations Density 0.021%

    No Known Activations