© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    plaque

    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
     oth
    -0.08
     tras
    -0.07
     �
    -0.07
     rehears
    -0.07
     bald
    -0.07
     Catar
    -0.07
    gaon
    -0.07
    ्यो
    -0.07
    ธ์
    -0.07
     sore
    -0.07
    POSITIVE LOGITS
     crypto
    0.07
    チ
    0.07
    -solid
    0.07
     pyro
    0.07
     ker
    0.07
     Planta
    0.07
     Wee
    0.07
    viert
    0.07
    �
    0.07
    118
    0.07
    Activations Density 0.001%

    No Known Activations