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. 109115
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
     kres
    -0.08
    (buf
    -0.08
     boutiques
    -0.08
     buffers
    -0.08
    -minded
    -0.07
     scratches
    -0.07
    ность
    -0.07
     insult
    -0.07
     datum
    -0.07
    nh
    -0.07
    POSITIVE LOGITS
     חבר
    0.09
    fred
    0.09
     cafeteria
    0.08
     وأكثر
    0.08
     sky
    0.08
    stay
    0.08
     שבע
    0.08
     الهواء
    0.08
    væ
    0.08
    או
    0.08
    Activations Density 0.077%

    No Known Activations