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. 90232
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Franklin
    -0.08
    ыты
    -0.08
     The
    -0.08
     يش
    -0.08
     Essay
    -0.07
     ধারণ
    -0.07
     This
    -0.07
     essay
    -0.07
    ्ञ
    -0.07
     open
    -0.07
    POSITIVE LOGITS
     inevitable
    0.08
    _NO
    0.08
    -No
    0.08
     neće
    0.08
     muligt
    0.08
     surpresa
    0.08
    crit
    0.08
    _SIM
    0.08
     inevitably
    0.08
    -no
    0.08
    Activations Density 0.004%

    No Known Activations