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. 104037
    Prev
    Next
    INDEX
    Explanations

    Ceramics, silicon nitride, turtles

    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
    _art
    -0.08
     fashioned
    -0.08
    έν
    -0.08
    .rich
    -0.07
     alat
    -0.07
    -art
    -0.07
    alarm
    -0.07
    oners
    -0.07
     reliant
    -0.07
    `.
    -0.07
    POSITIVE LOGITS
     atmosphere
    0.08
    _IPV
    0.08
     Devon
    0.08
     bactér
    0.08
    хэг
    0.08
    折
    0.08
     жоб
    0.08
     kerk
    0.08
     photon
    0.07
    ලු
    0.07
    Activations Density 0.001%

    No Known Activations