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. 65190
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    _REASON
    -0.07
     sâu
    -0.07
     pacing
    -0.07
    Flexible
    -0.07
     bitt
    -0.07
     massive
    -0.07
    Reblog
    -0.07
    ॥
    -0.07
     чувств
    -0.07
     أمر
    -0.07
    POSITIVE LOGITS
     �
    0.09
     /><
    0.08
     philosophie
    0.08
    并
    0.08
     页面
    0.08
     Ultimate
    0.08
    ixon
    0.08
    .pages
    0.07
     &_
    0.07
     الصفحة
    0.07
    Activations Density 0.045%

    No Known Activations