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. 26872
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
     Carolina
    -0.08
     novels
    -0.07
    IOC
    -0.07
    居
    -0.07
     당시
    -0.07
     damal
    -0.07
    教学
    -0.07
     urban
    -0.07
     લેખ
    -0.07
     laste
    -0.07
    POSITIVE LOGITS
    oret
    0.08
    ие
    0.08
    nem
    0.08
     PUR
    0.08
    oureux
    0.07
    _OP
    0.07
    .lng
    0.07
    åt
    0.07
    .op
    0.07
    glm
    0.07
    Activations Density 0.013%

    No Known Activations