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. 90246
    Prev
    Next
    INDEX
    Explanations

    School assignments and textbooks

    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
    indent
    -0.08
     কথ
    -0.07
    	List
    -0.07
    mean
    -0.07
    แข
    -0.07
     সৃষ্টি
    -0.07
     nyata
    -0.07
     seperti
    -0.07
    (call
    -0.07
    POSITIVE LOGITS
    ווח
    0.08
     ઘટના
    0.08
     passagem
    0.08
     નંબર
    0.08
     नंबर
    0.08
     canned
    0.08
     camping
    0.08
     ઉત્તર
    0.08
     پوليس
    0.08
     področ
    0.08
    Activations Density 0.009%

    No Known Activations