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. 111502
    Prev
    Next
    INDEX
    Explanations

    sur

    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
    lessness
    -0.08
     alph
    -0.08
    been
    -0.07
    Tunnel
    -0.07
     recess
    -0.07
    queued
    -0.07
     Gaut
    -0.07
     buzzing
    -0.07
     illustrated
    -0.07
    proced
    -0.07
    POSITIVE LOGITS
    -songwriter
    0.08
     Felipe
    0.07
    Demand
    0.07
    ייך
    0.07
     Cater
    0.07
     Peyton
    0.07
     Dhe
    0.07
     Pad
    0.07
     sou
    0.07
     placebo
    0.07
    Activations Density 0.017%

    No Known Activations