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. 622
    Prev
    Next
    INDEX
    Explanations

    move

    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
    ificates
    -0.09
     infant
    -0.08
     Hann
    -0.08
     squirrel
    -0.08
    ayat
    -0.07
     Hà
    -0.07
    760
    -0.07
    Sar
    -0.07
     gir
    -0.07
    adecimal
    -0.07
    POSITIVE LOGITS
     الب
    0.08
     вперед
    0.08
     объ
    0.07
    �
    0.07
    LR
    0.07
     appropr
    0.07
    яться
    0.07
    �
    0.07
     प्रतिस
    0.07
    rim
    0.07
    Activations Density 0.050%

    No Known Activations