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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120361
    Prev
    Next
    INDEX
    Explanations

    opathic

    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
    live
    -0.09
    cand
    -0.08
    /live
    -0.08
    shade
    -0.08
    sand
    -0.08
    zeuge
    -0.08
    ulad
    -0.08
     Maker
    -0.08
    date
    -0.07
    -0.07
    POSITIVE LOGITS
     dermatitis
    0.08
    .mybatisplus
    0.08
     નહીં
    0.08
     quiso
    0.08
     trem
    0.08
     unr
    0.08
     prie
    0.08
    の場合
    0.08
    .hikari
    0.08
     Lenn
    0.08
    Activations Density 0.010%

    No Known Activations