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. 131017
    Prev
    Next
    INDEX
    Explanations

    say 'oys'

    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
    lov
    -0.09
    649
    -0.08
    lih
    -0.08
     baking
    -0.08
    checkout
    -0.07
     vere
    -0.07
    ೀತಿ
    -0.07
    Mov
    -0.07
     funding
    -0.07
     coups
    -0.07
    POSITIVE LOGITS
    oy
    0.15
    oys
    0.15
    OY
    0.12
    irth
    0.11
    ੱਚ
    0.10
    ાળ
    0.10
    േ�
    0.10
    orn
    0.09
    ॉय
    0.09
    ેબ
    0.09
    Activations Density 0.001%

    No Known Activations