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. 45780
    Prev
    Next
    INDEX
    Explanations

    adjacent

    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
     jargon
    -0.08
     técnicos
    -0.08
    헌
    -0.07
    érature
    -0.07
     البريد
    -0.07
    יכה
    -0.07
     Alberta
    -0.07
     يعني
    -0.07
     Jacqueline
    -0.07
     Técnica
    -0.07
    POSITIVE LOGITS
     assertion
    0.08
     адв
    0.08
     суда
    0.07
     PSI
    0.07
    -ish
    0.07
     sef
    0.07
    Equality
    0.07
    mol
    0.07
    121
    0.07
    -sav
    0.07
    Activations Density 0.022%

    No Known Activations