© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    weather

    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
     Crawford
    -0.07
     travers
    -0.07
    🏼
    -0.07
    -exp
    -0.06
     धर्म
    -0.06
    (foo
    -0.06
     cope
    -0.06
     projekt
    -0.06
     cylinder
    -0.06
    Exponent
    -0.06
    POSITIVE LOGITS
     తద
    0.08
     sham
    0.08
     Laura
    0.08
     Sunny
    0.08
     Mitch
    0.08
    bericht
    0.08
     Serena
    0.08
    ippers
    0.07
     Meetings
    0.07
     sunny
    0.07
    Activations Density 0.022%

    No Known Activations