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. 119342
    Prev
    Next
    INDEX
    Explanations

    schema

    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
    IMPLE
    -0.08
     BASIS
    -0.08
     ausgestattet
    -0.08
    717
    -0.08
     PERSON
    -0.07
     trolley
    -0.07
    (iv
    -0.07
     wewe
    -0.07
     kanske
    -0.07
    bere
    -0.07
    POSITIVE LOGITS
     context
    0.08
    _context
    0.08
    namespace
    0.08
    context
    0.08
    	Context
    0.08
    achten
    0.08
     Kontext
    0.08
    Context
    0.08
    icity
    0.08
    	context
    0.08
    Activations Density 0.022%

    No Known Activations