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. 53943
    Prev
    Next
    INDEX
    Explanations

    /

    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
    ุ่ม
    -0.08
     zvi
    -0.08
     illuminating
    -0.08
     irradi
    -0.07
     interfaz
    -0.07
    结合
    -0.07
    liness
    -0.07
    ktrum
    -0.07
    zung
    -0.07
    śl
    -0.07
    POSITIVE LOGITS
     التس
    0.09
     মাস
    0.09
     Astros
    0.08
    ০
    0.08
     Miami
    0.08
    _owner
    0.08
    _last
    0.08
    Acct
    0.07
     anniversary
    0.07
    /W
    0.07
    Activations Density 0.015%

    No Known Activations