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. 12855
    Prev
    Next
    INDEX
    Explanations

    complex numbers

    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
     viz
    -0.08
     dak
    -0.08
    (DATA
    -0.07
     vzh
    -0.07
     মাঠ
    -0.07
     бл
    -0.07
     ceeb
    -0.07
     സമയ
    -0.07
    _SIGN
    -0.06
     ensinar
    -0.06
    POSITIVE LOGITS
    paired
    0.08
    outin
    0.08
    ోల
    0.08
     theirs
    0.08
     pump
    0.07
    Pairs
    0.07
    il
    0.07
    pesas
    0.07
     hers
    0.07
    ansom
    0.07
    Activations Density 0.009%

    No Known Activations