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. 11-RESID-POST-AA
    6. 112562
    Prev
    Next
    INDEX
    Explanations

    Nitrogen

    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
    -0.08
     vertra
    -0.08
     які
    -0.08
    CADE
    -0.07
    网
    -0.07
     redd
    -0.07
     swal
    -0.07
     pilotes
    -0.07
     brut
    -0.07
     Switch
    -0.07
    POSITIVE LOGITS
     लगाया
    0.08
    -rich
    0.08
    -energy
    0.08
    -gl
    0.07
     sentencia
    0.07
     необходимых
    0.07
    Needed
    0.07
     nitrogen
    0.07
    -half
    0.07
     влад
    0.07
    Activations Density 0.002%

    No Known Activations