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. 45692
    Prev
    Next
    INDEX
    Explanations

    .

    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
     മാറ
    -0.08
    phoon
    -0.07
    িক্ষ
    -0.07
     پوری
    -0.07
     collider
    -0.07
     внес
    -0.07
    _FLAG
    -0.07
     apag
    -0.07
    ਰ
    -0.07
    ਕਾਰ
    -0.07
    POSITIVE LOGITS
     gist
    0.08
     Em
    0.08
    Draft
    0.08
     detaill
    0.08
    Em
    0.07
     includes
    0.07
    เน
    0.07
     באנ
    0.07
     उच्च
    0.07
     नेपाली
    0.07
    Activations Density 0.210%

    No Known Activations