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. 106232
    Prev
    Next
    INDEX
    Explanations

    blooming

    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
     poved
    -0.08
     잡
    -0.08
    evil
    -0.08
    YY
    -0.07
    hon
    -0.07
     removes
    -0.07
    Parcel
    -0.07
    -0.07
     Funny
    -0.07
    pv
    -0.07
    POSITIVE LOGITS
     Bloom
    0.09
    盛
    0.09
     bloom
    0.09
     sáng
    0.09
     blooming
    0.08
    तम
    0.08
     Kling
    0.08
     bel
    0.08
     happening
    0.08
     spectacular
    0.08
    Activations Density 0.007%

    No Known Activations