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. 29798
    Prev
    Next
    INDEX
    Explanations

    writing perspective

    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
     قيمة
    -0.08
     подпис
    -0.08
    :param
    -0.08
     smoker
    -0.07
     کاهش
    -0.07
     फैल
    -0.07
    @param
    -0.07
    	display
    -0.07
     investering
    -0.07
     منتشر
    -0.07
    POSITIVE LOGITS
     الثالثة
    0.09
     voix
    0.09
    统
    0.09
     locus
    0.09
     autobi
    0.08
     മൂന്ന
    0.08
    experienced
    0.08
     пове
    0.08
     experien
    0.08
    六
    0.08
    Activations Density 0.033%

    No Known Activations