© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68188
    Prev
    Next
    INDEX
    Explanations

    Chi-square distribution

    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
     interventions
    -0.09
    지가
    -0.07
     textiles
    -0.07
     privées
    -0.07
     Britain
    -0.07
    지를
    -0.07
    .config
    -0.07
    .ibatis
    -0.07
     Danmark
    -0.07
     اليوم
    -0.07
    POSITIVE LOGITS
     Burr
    0.09
     estren
    0.09
     PTSD
    0.08
     burr
    0.08
     kurt
    0.08
    đen
    0.08
     porod
    0.08
    ceral
    0.08
    plot
    0.07
     inhale
    0.07
    Activations Density 0.002%

    No Known Activations