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. 9196
    Prev
    Next
    INDEX
    Explanations

    characters and letters

    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
     Designer
    -0.09
     Pentagon
    -0.09
    Designer
    -0.08
    ibraries
    -0.08
    Libraries
    -0.08
     Libraries
    -0.08
     Presidents
    -0.08
     relief
    -0.07
     Producers
    -0.07
    (DIS
    -0.07
    POSITIVE LOGITS
     ಉಪ
    0.09
     gedeelt
    0.09
     মিল
    0.08
     ఉప
    0.08
     případ
    0.08
     মধ্য
    0.08
     teilweise
    0.08
     onder
    0.08
     సంప
    0.08
     మధ్య
    0.08
    Activations Density 0.002%

    No Known Activations