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. 130955
    Prev
    Next
    INDEX
    Explanations

    지

    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
    antics
    -0.08
     За
    -0.08
    koliko
    -0.08
     Ges
    -0.07
    aculture
    -0.07
     चोरी
    -0.07
    atisation
    -0.07
    Haha
    -0.07
    ಸ್ತಿ
    -0.07
     Գ
    -0.07
    POSITIVE LOGITS
     않는
    0.14
     않
    0.12
    능
    0.12
     않습니다
    0.12
     않을
    0.12
    켜
    0.12
     않는다
    0.12
    უსტად
    0.11
    ্ঞান
    0.11
     않은
    0.11
    Activations Density 0.001%

    No Known Activations