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. 114005
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
    alte
    -0.09
    ือง
    -0.08
    altungen
    -0.08
     HAND
    -0.08
     nâng
    -0.08
    Wing
    -0.08
     מקר
    -0.08
    phants
    -0.08
    اضة
    -0.08
    wachung
    -0.08
    POSITIVE LOGITS
     replied
    0.08
     Levi
    0.08
     converse
    0.07
     gedacht
    0.07
     anyway
    0.07
     তুমি
    0.07
     الحقيقة
    0.07
     Menn
    0.07
    _REPLY
    0.07
     Calm
    0.07
    Activations Density 0.094%

    No Known Activations