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. 112323
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    express
    -0.08
    Recording
    -0.07
     ضروری
    -0.07
    Flutter
    -0.07
    _TARGET
    -0.07
    467
    -0.07
    selen
    -0.07
    sequence
    -0.07
    poq
    -0.07
    target
    -0.07
    POSITIVE LOGITS
     irraa
    0.09
     schließlich
    0.08
     Lastly
    0.08
     absch
    0.08
     concludes
    0.08
     Finally
    0.08
     letzt
    0.08
     ಕಳೆದ
    0.08
    еды
    0.08
     kopp
    0.08
    Activations Density 0.005%

    No Known Activations