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. 130976
    Prev
    Next
    INDEX
    Explanations

    say age

    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
    úil
    -0.10
    롭게
    -0.09
    étaire
    -0.09
     قائد
    -0.08
    étaires
    -0.08
    blica
    -0.08
    ительного
    -0.08
    افته
    -0.08
    ुभयो
    -0.08
    ález
    -0.08
    POSITIVE LOGITS
    િંગ
    0.23
    age
    0.23
    ирование
    0.22
    िंग
    0.22
    িং
    0.22
    ਿੰਗ
    0.21
    ింగ్
    0.20
    инг
    0.20
    ಿಂಗ್
    0.20
    ിംഗ്
    0.20
    Activations Density 0.027%

    No Known Activations