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. 43122
    Prev
    Next
    INDEX
    Explanations

    gold

    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
     causada
    -0.09
     CAC
    -0.08
     সমস্য
    -0.07
     segura
    -0.07
     texting
    -0.07
     edgy
    -0.07
     vibe
    -0.07
     Stone
    -0.07
     stabbing
    -0.07
    side
    -0.07
    POSITIVE LOGITS
     Baghdad
    0.09
    金花
    0.08
     içinde
    0.08
     рисун
    0.08
    ਾਡੇ
    0.08
     enhancing
    0.08
     embroidery
    0.08
     CHtml
    0.08
    ুক্ত
    0.08
    0.08
    Activations Density 0.007%

    No Known Activations