© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2518
    Prev
    Next
    INDEX
    Explanations

    rés

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soi
    -0.09
     epit
    -0.09
     afin
    -0.08
    함
    -0.08
     vali
    -0.08
     Todd
    -0.08
     tomadas
    -0.07
    CID
    -0.07
     Aspir
    -0.07
    Definitions
    -0.07
    POSITIVE LOGITS
    主体
    0.09
    390
    0.07
     سل
    0.07
    \widgets
    0.07
     Kata
    0.07
    909
    0.07
    Ink
    0.07
     kör
    0.07
    0.07
     یو
    0.07
    Activations Density 0.000%
    No Known Activations