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

    Neuronpedia

    APICircuit 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. 75916
    Prev
    Next
    INDEX
    Explanations

    promote

    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
    گیر
    -0.08
    স্ব
    -0.08
    bun
    -0.08
    grp
    -0.08
    -0.07
     Gord
    -0.07
     ater
    -0.07
     Manu
    -0.07
    夹
    -0.07
    _plate
    -0.07
    POSITIVE LOGITS
    ერ
    0.08
    nas
    0.08
     sper
    0.08
    推广
    0.08
    渠道
    0.08
    ात्मक
    0.08
     funnel
    0.08
     slogan
    0.08
     slogans
    0.07
    ции
    0.07
    Activations Density 0.023%

    No Known Activations