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. 377
    Prev
    Next
    INDEX
    Explanations

    os

    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
    �
    -0.08
     UPS
    -0.07
     lez
    -0.07
     Montes
    -0.07
    	label
    -0.07
     ak
    -0.07
     humanity
    -0.07
     Bake
    -0.07
     vý
    -0.07
     Burke
    -0.07
    POSITIVE LOGITS
    ativo
    0.08
    леж
    0.08
    ipt
    0.08
    orientation
    0.08
     influ
    0.07
    Decoder
    0.07
     contemplation
    0.07
     '~/
    0.07
    izon
    0.07
    ativos
    0.07
    Activations Density 0.001%

    No Known Activations