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. 9249
    Prev
    Next
    INDEX
    Explanations

    GCD calculations

    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
    Boost
    -0.08
     Swan
    -0.08
     szüks
    -0.08
     BOOST
    -0.08
     sıra
    -0.08
    BOOST
    -0.08
    .Mapping
    -0.07
     boosting
    -0.07
    .need
    -0.07
    -js
    -0.07
    POSITIVE LOGITS
     comparte
    0.09
     região
    0.08
    प्रत
    0.08
    рот
    0.08
     query
    0.08
    ق
    0.08
     shares
    0.08
    blood
    0.07
     Streit
    0.07
     वो
    0.07
    Activations Density 0.020%

    No Known Activations