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. 59307
    Prev
    Next
    INDEX
    Explanations

    Hormones

    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
     কোন
    -0.09
    haften
    -0.08
    哪个公司
    -0.08
     сказал
    -0.08
     impressions
    -0.07
     કહ્યું
    -0.07
    ুকে
    -0.07
     shove
    -0.07
     Exotic
    -0.07
    busters
    -0.07
    POSITIVE LOGITS
    女性
    0.12
     സ്ത്രീ
    0.11
     మహిళ
    0.11
     여성
    0.11
     menstrual
    0.11
     女性
    0.11
     menstru
    0.10
     பெண
    0.10
     महिलाओं
    0.10
    女人
    0.10
    Activations Density 0.016%

    No Known Activations