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. 90077
    Prev
    Next
    INDEX
    Explanations

    shade

    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
    .warn
    -0.09
     billed
    -0.08
     gog
    -0.08
     tonos
    -0.07
     बो
    -0.07
    .co
    -0.07
     paycheck
    -0.07
    .meta
    -0.07
    	g
    -0.07
    ါ
    -0.07
    POSITIVE LOGITS
     sheltered
    0.10
     shielding
    0.10
     niches
    0.09
     respite
    0.09
    建筑
    0.09
     shafts
    0.08
     shelter
    0.08
     huts
    0.08
    区域
    0.08
     afternoon
    0.08
    Activations Density 0.011%

    No Known Activations