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. 77545
    Prev
    Next
    INDEX
    Explanations

    Overwatch characters

    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
    [state
    -0.08
     mln
    -0.08
     drying
    -0.07
     nisi
    -0.07
     proprietary
    -0.07
     nch
    -0.07
    .factor
    -0.07
     theses
    -0.07
    ossos
    -0.07
    182
    -0.07
    POSITIVE LOGITS
    弟
    0.08
     באנ
    0.08
    locale
    0.08
     Allies
    0.08
     সৈ
    0.08
     ingr
    0.08
     misch
    0.08
     He's
    0.08
     আনন্দ
    0.08
    				
    ↵
    0.08
    Activations Density 0.002%

    No Known Activations