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. 12693
    Prev
    Next
    INDEX
    Explanations

    Coffee shop image prompts

    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
     notwithstanding
    -0.08
     unquestion
    -0.08
     ఎన
    -0.08
     וב
    -0.08
    ρης
    -0.07
     конечно
    -0.07
    UND
    -0.07
     وعدم
    -0.07
     المض
    -0.07
    ण्ड
    -0.07
    POSITIVE LOGITS
     apreci
    0.08
    interesting
    0.07
     Golden
    0.07
     preparados
    0.07
     leisurely
    0.07
     hovered
    0.07
     Filled
    0.07
    Golden
    0.07
     disfrutar
    0.07
    hul
    0.07
    Activations Density 0.006%

    No Known Activations