© 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. 54776
    Prev
    Next
    INDEX
    Explanations

    sums and equations

    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
     спир
    -0.08
    Pricing
    -0.08
     совершен
    -0.08
     масло
    -0.08
     offerte
    -0.08
     камера
    -0.08
    چر
    -0.07
     parceiros
    -0.07
     hore
    -0.07
     пит
    -0.07
    POSITIVE LOGITS
     imbalance
    0.11
    净
    0.10
    resultado
    0.10
    imbal
    0.09
    aggreg
    0.09
    余额
    0.09
    -net
    0.09
     netto
    0.09
     resultat
    0.09
    net
    0.09
    Activations Density 0.054%

    No Known Activations