Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129817
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    issimi
    -0.08
    ’espère
    -0.08
    issa
    -0.07
     kurzem
    -0.07
     literal
    -0.07
     Literal
    -0.07
     چاپ
    -0.07
     мерз
    -0.07
     kapp
    -0.07
     Bob
    -0.07
    POSITIVE LOGITS
     перейти
    0.08
    alth
    0.08
     başlayan
    0.08
     comercio
    0.08
     restantes
    0.08
     finer
    0.08
    Beyond
    0.08
    onten
    0.08
     onwards
    0.08
     noites
    0.08
    Activations Density 0.069%

    No Known Activations