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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 43996
    Prev
    Next
    INDEX
    Explanations

    motions

    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
     ethn
    -0.08
     analyses
    -0.08
     gateways
    -0.08
     gateway
    -0.08
     সাং
    -0.08
    人才
    -0.08
    Lottery
    -0.07
    analytics
    -0.07
     peuvent
    -0.07
    ‏
    -0.07
    POSITIVE LOGITS
     doucement
    0.11
     abdomen
    0.10
    护理
    0.10
     Carefully
    0.10
     swirling
    0.10
     Clip
    0.10
    按摩
    0.10
     gently
    0.09
     धीरे
    0.09
     акку
    0.09
    Activations Density 0.044%

    No Known Activations