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. 9104
    Prev
    Next
    INDEX
    Explanations

    AI assistant/providing content

    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
    和平
    -0.08
     combinations
    -0.08
    ;↵↵//
    -0.07
    abil
    -0.07
     variations
    -0.07
     affects
    -0.07
     भाज
    -0.07
     bens
    -0.07
    enders
    -0.07
     vegetables
    -0.07
    POSITIVE LOGITS
     شركة
    0.08
     squeezed
    0.08
    Pc
    0.08
    Solic
    0.08
    Reporte
    0.08
     музык
    0.08
    لاقة
    0.08
    Hr
    0.08
    clip
    0.08
     Siri
    0.08
    Activations Density 0.291%

    No Known Activations