Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76023
    Prev
    Next
    INDEX
    Explanations

    computer software

    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
     psychic
    -0.08
    قيقي
    -0.07
     især
    -0.07
     машине
    -0.07
     literalmente
    -0.07
     City's
    -0.07
     someone's
    -0.07
     auxili
    -0.07
     xpath
    -0.07
     beams
    -0.07
    POSITIVE LOGITS
     সফ
    0.10
     software
    0.10
    software
    0.10
     firmware
    0.09
     Software
    0.08
    glomer
    0.08
    _cpp
    0.08
    Software
    0.08
     Infiniti
    0.08
    软件
    0.08
    Activations Density 0.133%

    No Known Activations