© 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. 7-RESID-POST-AA
    11. 1459
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     থাকে
    -0.08
    ீர
    -0.08
     neste
    -0.08
     lok
    -0.07
     dichtbij
    -0.07
    idus
    -0.07
     prossimo
    -0.07
     Rece
    -0.07
     Templates
    -0.07
     এগ
    -0.07
    POSITIVE LOGITS
     originated
    0.08
     подс
    0.08
     ảnh
    0.08
     chiefly
    0.07
     pls
    0.07
    .origin
    0.07
     beruh
    0.07
     вечер
    0.07
     buff
    0.07
    की
    0.07
    Activations Density 0.122%

    No Known Activations