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. 12669
    Prev
    Next
    INDEX
    Explanations

    Monika dialogues

    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
     Lifecycle
    -0.09
     生命周期
    -0.08
     həyat
    -0.08
     biopsy
    -0.08
     yaşam
    -0.08
     خواب
    -0.08
     ایل
    -0.08
     Lone
    -0.08
     newborn
    -0.08
     noma
    -0.08
    POSITIVE LOGITS
     frente
    0.08
     undermine
    0.07
     aesthetic
    0.07
    acca
    0.07
    .Buffer
    0.07
    スタッフ
    0.07
    ftware
    0.07
     Pupp
    0.07
     Ts
    0.07
    _ini
    0.07
    Activations Density 0.007%

    No Known Activations