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. 49550
    Prev
    Next
    INDEX
    Explanations

    PY

    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
     vigilant
    -0.07
     loyal
    -0.07
     Sam
    -0.07
     ken
    -0.07
     Mot
    -0.07
     intuit
    -0.07
     greedy
    -0.07
     Pascal
    -0.07
     Gö
    -0.07
     Mat
    -0.07
    POSITIVE LOGITS
     nachdem
    0.08
     це
    0.08
     davon
    0.08
    onavirus
    0.07
    .Msg
    0.07
    .any
    0.07
     бы
    0.07
    .Mapping
    0.07
     estavam
    0.07
    .kind
    0.07
    Activations Density 0.000%

    No Known Activations