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. 112315
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    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
    елі
    -0.08
    gema
    -0.08
    .met
    -0.08
    標
    -0.08
     aki
    -0.08
    retch
    -0.07
    imba
    -0.07
     exploiting
    -0.07
     mosa
    -0.07
     potenci
    -0.07
    POSITIVE LOGITS
    ですね
    0.08
     olmaz
    0.08
     bath
    0.08
     dolls
    0.08
    _core
    0.08
     ആയി
    0.07
     الول
    0.07
     यानी
    0.07
     Ie
    0.07
    Ie
    0.07
    Activations Density 0.043%

    No Known Activations