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. 45065
    Prev
    Next
    INDEX
    Explanations

    sports coaching

    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
     Mesmo
    -0.08
     kroz
    -0.08
    icano
    -0.07
    -envelope
    -0.07
    xlabel
    -0.07
     weken
    -0.07
     Experts
    -0.07
    ога
    -0.07
    .Me
    -0.07
     xlabel
    -0.07
    POSITIVE LOGITS
     hotspots
    0.09
    Sequential
    0.08
    热点
    0.08
    akash
    0.08
     પૂર્વ
    0.08
     apuestas
    0.07
     stint
    0.07
     promising
    0.07
     முன
    0.07
     bidi
    0.07
    Activations Density 0.018%

    No Known Activations