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. 58680
    Prev
    Next
    INDEX
    Explanations

    sentence fragments, conversational filler

    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
    istra
    -0.08
     disrupting
    -0.08
     obtainable
    -0.08
    lər
    -0.07
     shattered
    -0.07
    orse
    -0.07
    ిశ
    -0.07
    ισ
    -0.07
     recognizable
    -0.07
     fija
    -0.07
    POSITIVE LOGITS
     chodzi
    0.09
     looph
    0.09
    bagai
    0.08
     비롯
    0.08
     Chuck
    0.08
    涉及
    0.08
    关键
    0.08
     voordeel
    0.07
    Ẩ
    0.07
    	bean
    0.07
    Activations Density 0.032%

    No Known Activations