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. 27706
    Prev
    Next
    INDEX
    Explanations

    Eyes and night vision

    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
     frustrated
    -0.08
     pressured
    -0.08
    ussing
    -0.07
     rosas
    -0.07
     atual
    -0.07
    <tag
    -0.07
    íns
    -0.07
    ഴിക്ക
    -0.07
    'entre
    -0.07
    PAY
    -0.07
    POSITIVE LOGITS
     adaptée
    0.09
     adapté
    0.09
     מתאים
    0.09
     адап
    0.09
    ாவில்
    0.08
     القديم
    0.08
     adaptés
    0.08
     accl
    0.08
     รอง
    0.08
     společnosti
    0.08
    Activations Density 0.003%

    No Known Activations