© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26085
    Prev
    Next
    INDEX
    Explanations

    Bullet points

    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
     একটু
    -0.10
     trochu
    -0.08
     थोड़ा
    -0.08
    ейчас
    -0.08
     hieman
    -0.08
     قلي
    -0.08
     આપણ
    -0.07
     यही
    -0.07
     थो
    -0.07
     chanc
    -0.07
    POSITIVE LOGITS
     Successfully
    0.12
    Successfully
    0.12
     expertly
    0.10
     drove
    0.10
     담당
    0.10
     успешно
    0.10
     proficient
    0.10
     revamped
    0.09
     •
    0.09
     adept
    0.09
    Activations Density 0.037%

    No Known Activations