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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 30689
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    PROFILE
    -0.08
     beschikken
    -0.08
    Lifestyle
    -0.08
     Malone
    -0.08
    gid
    -0.08
     renowned
    -0.07
     notorious
    -0.07
    Concurrent
    -0.07
    Journey
    -0.07
    -0.07
    POSITIVE LOGITS
     обознач
    0.09
     denotes
    0.09
    */,↵
    0.08
     doucement
    0.08
     khe
    0.08
     தலைம
    0.08
     hipótese
    0.08
    ]^
    0.08
     hipó
    0.08
     персона
    0.07
    Activations Density 0.004%

    No Known Activations