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. 12572
    Prev
    Next
    INDEX
    Explanations

    app

    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
     Sidney
    -0.08
     உள்ள
    -0.08
     Misc
    -0.08
     Chrys
    -0.08
     unpack
    -0.07
     Tengo
    -0.07
     இ
    -0.07
    cimentos
    -0.07
     INNER
    -0.07
     sentado
    -0.07
    POSITIVE LOGITS
    <void
    0.09
    edy
    0.08
     plateforme
    0.08
     клуба
    0.08
     klachten
    0.08
    .club
    0.08
     newsletter
    0.08
     attractive
    0.08
    上线
    0.08
     nutzen
    0.07
    Activations Density 0.040%

    No Known Activations