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. 111774
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     Brett
    -0.08
     intimacy
    -0.07
    芽
    -0.07
    edora
    -0.07
     spam
    -0.07
    Batman
    -0.07
     bushes
    -0.07
    宋
    -0.07
     STI
    -0.07
     socialize
    -0.07
    POSITIVE LOGITS
     Rubber
    0.09
     Road
    0.08
     impér
    0.08
     ONLINE
    0.08
     rubber
    0.08
     road
    0.08
     prél
    0.07
     retard
    0.07
     heath
    0.07
    road
    0.07
    Activations Density 0.039%

    No Known Activations