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. 29965
    Prev
    Next
    INDEX
    Explanations

    therefore

    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
     speed
    -0.09
     admire
    -0.09
    รุ่ง
    -0.08
     Speed
    -0.08
     kreativ
    -0.08
     mide
    -0.08
    _speed
    -0.08
    แรง
    -0.08
     välja
    -0.08
     ela
    -0.08
    POSITIVE LOGITS
    ером
    0.08
    (_:
    0.08
    Near
    0.08
     near
    0.08
    (annotation
    0.08
     мож
    0.08
     Near
    0.08
     пос
    0.07
    期間
    0.07
     enkelte
    0.07
    Activations Density 0.001%

    No Known Activations