© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    -we

    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
     clergy
    -0.08
     bur
    -0.08
     prized
    -0.07
     Sleeve
    -0.07
     anzeigen
    -0.07
     surf
    -0.07
    (bean
    -0.07
    mobil
    -0.07
    리지
    -0.07
     sleeve
    -0.07
    POSITIVE LOGITS
     stati
    0.08
     �
    0.08
    aspersky
    0.08
     అన
    0.08
    ition
    0.07
     همچنین
    0.07
     sunt
    0.07
     با
    0.07
     Motorsport
    0.07
     Sho
    0.07
    Activations Density 0.002%

    No Known Activations