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. 119202
    Prev
    Next
    INDEX
    Explanations

    announcements and advertisements

    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
    ritz
    -0.09
    heim
    -0.08
     pounding
    -0.07
    amanya
    -0.07
     negociar
    -0.07
    edir
    -0.07
    ிப்ப
    -0.07
    하기
    -0.07
    itized
    -0.07
     ಭ
    -0.07
    POSITIVE LOGITS
     Micro
    0.09
     konse
    0.08
    Micro
    0.08
     Boutique
    0.08
     conseqü
    0.08
    ucion
    0.08
    ░
    0.08
    ंब
    0.08
     Clone
    0.07
     Lite
    0.07
    Activations Density 0.027%

    No Known Activations