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. 49359
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     hijo
    -0.08
     Palm
    -0.08
     শিশু
    -0.07
     ליל
    -0.07
     niños
    -0.07
     dusk
    -0.07
    ämään
    -0.07
    Salon
    -0.07
    子
    -0.07
    、安全
    -0.07
    POSITIVE LOGITS
    258
    0.09
     Line
    0.08
    avag
    0.07
     приз
    0.07
    (line
    0.07
    157
    0.07
    ithub
    0.07
    gruppen
    0.07
    graded
    0.07
    626
    0.07
    Activations Density 0.049%

    No Known Activations