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. 98163
    Prev
    Next
    INDEX
    Explanations

    1

    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
    烧
    -0.08
    docker
    -0.08
     Dumneze
    -0.08
     fights
    -0.07
    రీ
    -0.07
     combat
    -0.07
    ским
    -0.07
    мун
    -0.07
    ిత్ర
    -0.07
    ибка
    -0.07
    POSITIVE LOGITS
     |
    0.11
     CLASS
    0.10
    	intent
    0.09
     SESSION
    0.09
     PROCED
    0.09
    _CONTROLLER
    0.09
     PRESENT
    0.08
    	system
    0.08
     PROVID
    0.08
     PURPOSE
    0.08
    Activations Density 0.014%

    No Known Activations