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. 111594
    Prev
    Next
    INDEX
    Explanations

    .

    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
     несп
    -0.09
     अपर
    -0.09
     нож
    -0.09
     ongel
    -0.09
     schein
    -0.09
     audition
    -0.09
     antagonist
    -0.09
     Brus
    -0.09
     Gesam
    -0.09
     Photoshop
    -0.09
    POSITIVE LOGITS
    Telemetry
    0.10
    Analytics
    0.09
    Auto
    0.09
    auto
    0.09
     latency
    0.09
    -sdk
    0.09
    Logging
    0.09
    _reporting
    0.08
    SDK
    0.08
     SDK
    0.08
    Activations Density 0.005%

    No Known Activations