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. 76447
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    事项
    -0.08
     hadis
    -0.07
    faa
    -0.07
     communal
    -0.07
     revenir
    -0.07
     Rag
    -0.07
     Hao
    -0.07
    Flying
    -0.07
    अपने
    -0.07
    DAP
    -0.07
    POSITIVE LOGITS
     xsi
    0.08
    mn
    0.08
     <$>
    0.08
    	 ↵
    0.08
    -priced
    0.07
    ζ
    0.07
    逐
    0.07
     xor
    0.07
     modulo
    0.07
     ζ
    0.07
    Activations Density 0.105%

    No Known Activations