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. 65775
    Prev
    Next
    INDEX
    Explanations

    zest

    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
    ठ
    -0.08
    .yml
    -0.07
    喝
    -0.07
    .find
    -0.07
     approx
    -0.07
     Stafford
    -0.07
     Ler
    -0.07
     Lending
    -0.07
     encontrar
    -0.07
     tarda
    -0.07
    POSITIVE LOGITS
     getaway
    0.09
     باعث
    0.08
     bestowed
    0.08
     energi
    0.08
     proudly
    0.08
     Ч
    0.08
    	Delete
    0.07
     золот
    0.07
    fur
    0.07
     proud
    0.07
    Activations Density 0.002%

    No Known Activations