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. 77253
    Prev
    Next
    INDEX
    Explanations

    multiple

    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
    ධ්
    -0.08
     conjug
    -0.08
    nod
    -0.08
    593
    -0.08
    Animating
    -0.08
    594
    -0.08
     ajax
    -0.07
    	url
    -0.07
    人物
    -0.07
     CLLocation
    -0.07
    POSITIVE LOGITS
    隔
    0.11
     Isolation
    0.11
     isolation
    0.11
     segreg
    0.11
     isolates
    0.10
    tenant
    0.10
    Isolation
    0.10
     izol
    0.10
     tenants
    0.10
     multiplex
    0.10
    Activations Density 0.018%

    No Known Activations