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. 12022
    Prev
    Next
    INDEX
    Explanations

    describing a girl's appearance

    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
    공
    -0.08
    136
    -0.08
    .router
    -0.08
    -speaking
    -0.08
    .calls
    -0.07
    Renew
    -0.07
     composer
    -0.07
    416
    -0.07
    .iot
    -0.07
     representing
    -0.07
    POSITIVE LOGITS
     ಮಟ್ಟ
    0.10
     уровня
    0.10
     nivå
    0.09
     수준
    0.09
    级
    0.09
    程度
    0.09
     nivel
    0.09
     horizon
    0.09
     деңгей
    0.09
    まで
    0.09
    Activations Density 0.013%

    No Known Activations