© 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. 11-RESID-POST-AA
    11. 94895
    Prev
    Next
    INDEX
    Explanations

    fruit

    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
     nung
    -0.08
     lisäksi
    -0.08
    .entry
    -0.08
    스토
    -0.08
     Rodgers
    -0.08
    имо
    -0.08
     astfel
    -0.08
    ippi
    -0.07
     fundamento
    -0.07
     sobres
    -0.07
    POSITIVE LOGITS
    자인
    0.09
     yakni
    0.08
     namely
    0.08
     yaitu
    0.08
     হিসেবে
    0.08
     namens
    0.07
     бах
    0.07
    ousal
    0.07
    aum
    0.07
     الـ
    0.07
    Activations Density 0.502%

    No Known Activations