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. 76543
    Prev
    Next
    INDEX
    Explanations

    download information file instructions

    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
     bowls
    -0.08
    .targets
    -0.08
     ટેસ્ટ
    -0.08
     ferme
    -0.08
    .speed
    -0.08
     eyebrows
    -0.07
    Shipping
    -0.07
     surfaces
    -0.07
     switches
    -0.07
     GPUs
    -0.07
    POSITIVE LOGITS
    (Calendar
    0.09
    (period
    0.08
     negoc
    0.08
    ného
    0.08
     litt
    0.08
    就是
    0.08
     integração
    0.08
     }).
    0.08
    (event
    0.08
     आर्थिक
    0.08
    Activations Density 0.004%

    No Known Activations