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. 58178
    Prev
    Next
    INDEX
    Explanations

    water

    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
    _wire
    -0.08
    _es
    -0.08
    raad
    -0.07
     holistic
    -0.07
     radically
    -0.07
    ored
    -0.07
     Welch
    -0.07
    _seed
    -0.07
    _cur
    -0.07
     gör
    -0.07
    POSITIVE LOGITS
    -relative
    0.10
     apan
    0.08
    .publish
    0.08
    0.08
     Nevertheless
    0.08
     aturan
    0.08
     மண
    0.07
     servlet
    0.07
     নিজেদের
    0.07
     personn
    0.07
    Activations Density 0.004%

    No Known Activations