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. 43476
    Prev
    Next
    INDEX
    Explanations

    Adaptation and evolution

    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
    kaz
    -0.08
    unctuation
    -0.08
     Achievement
    -0.08
    .viewmodel
    -0.08
    .openc
    -0.08
    gatsby
    -0.08
    成绩
    -0.08
    =torch
    -0.08
     Brandon
    -0.08
    .Math
    -0.08
    POSITIVE LOGITS
     attackers
    0.17
     ആക്രമ
    0.17
     malware
    0.16
    攻击
    0.16
     હુમ
    0.16
     saldır
    0.16
     amenazas
    0.15
     advers
    0.15
     threats
    0.15
     attacks
    0.15
    Activations Density 0.029%

    No Known Activations