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. 77496
    Prev
    Next
    INDEX
    Explanations

    triangle

    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
     Verdict
    -0.08
     Symphony
    -0.07
    Mn
    -0.07
     Courtney
    -0.07
    \Type
    -0.07
     Cul
    -0.07
    Nou
    -0.07
     Lt
    -0.07
    Lie
    -0.07
     notably
    -0.07
    POSITIVE LOGITS
     detenido
    0.08
     stared
    0.08
    ,对于
    0.08
     diámetro
    0.08
     әкім
    0.08
     正
    0.07
     башкар
    0.07
    عضاء
    0.07
    _v
    0.07
     Arabia
    0.07
    Activations Density 0.008%

    No Known Activations