Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44450
    Prev
    Next
    INDEX
    Explanations

    да

    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
     Wilm
    -0.07
     crocod
    -0.07
     경찰
    -0.07
    Previously
    -0.07
     Microwave
    -0.07
    tema
    -0.07
     flick
    -0.07
    prache
    -0.07
     sauna
    -0.07
    	The
    -0.07
    POSITIVE LOGITS
     setuptools
    0.11
     packaging
    0.08
     发布
    0.08
    出版
    0.08
    uptools
    0.08
    ellectual
    0.08
     alumni
    0.08
    endaft
    0.08
     Intellectual
    0.07
    Publish
    0.07
    Activations Density 0.004%

    No Known Activations