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. 60490
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
    Mc
    -0.08
    Mig
    -0.08
     comfortabel
    -0.08
    Cru
    -0.08
    Comfort
    -0.07
    Random
    -0.07
     stärken
    -0.07
    CAT
    -0.07
    žete
    -0.07
     lack
    -0.07
    POSITIVE LOGITS
     Ваш
    0.08
    .OK
    0.08
     Наш
    0.07
     Isto
    0.07
     Providing
    0.07
    창
    0.07
     Gespräch
    0.07
    ान
    0.07
     уваж
    0.07
     casc
    0.07
    Activations Density 0.001%

    No Known Activations