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. 9037
    Prev
    Next
    INDEX
    Explanations

    Did

    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
     manipulated
    -0.08
     Wor
    -0.08
    styl
    -0.08
     Fab
    -0.07
     Cary
    -0.07
    Geo
    -0.07
     Structured
    -0.07
    lear
    -0.07
     Marina
    -0.07
    grain
    -0.07
    POSITIVE LOGITS
     Crab
    0.08
    akin
    0.07
    actic
    0.07
     recently
    0.07
     наг
    0.07
     afore
    0.07
    .characters
    0.07
     Robbins
    0.07
    ETF
    0.07
     Levy
    0.07
    Activations Density 0.052%

    No Known Activations