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. 23-RESID-POST-AA
    6. 130932
    Prev
    Next
    INDEX
    Explanations

    say "Armor"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    面
    -0.09
    面的
    -0.09
    oter
    -0.07
     وجه
    -0.07
    Fac
    -0.07
    ման
    -0.07
    Rev
    -0.07
     faced
    -0.07
     επικ
    -0.07
     poll
    -0.07
    POSITIVE LOGITS
    Armor
    0.14
    armor
    0.13
     Armor
    0.12
     armor
    0.12
    ARING
    0.09
     armored
    0.08
     ধৰ
    0.08
     әп
    0.08
     Armour
    0.08
    ẹgẹ
    0.08
    Activations Density 0.000%

    No Known Activations