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. 87
    Prev
    Next
    INDEX
    Explanations

    bar

    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
     feasibility
    -0.07
    .namespace
    -0.07
    .export
    -0.07
     scaffold
    -0.07
    .bulk
    -0.07
     Prepare
    -0.07
    _finalize
    -0.07
     wastewater
    -0.07
    ématiques
    -0.07
     Emerald
    -0.07
    POSITIVE LOGITS
     diminution
    0.09
     Hamburger
    0.09
     geg
    0.08
     Lena
    0.08
     terrestre
    0.08
     sucked
    0.08
     Hör
    0.07
     मौसम
    0.07
     dismin
    0.07
     Repub
    0.07
    Activations Density 0.005%

    No Known Activations