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. 55916
    Prev
    Next
    INDEX
    Explanations

    ozone

    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
    .import
    -0.08
    Give
    -0.08
    elses
    -0.08
    .g
    -0.08
    solar
    -0.07
    Giving
    -0.07
    nad
    -0.07
     Volcano
    -0.07
    Solar
    -0.07
     giving
    -0.07
    POSITIVE LOGITS
     optimise
    0.08
     пользователя
    0.08
    された
    0.07
     optimisation
    0.07
     пользователей
    0.07
     hoş
    0.07
    <?=
    0.07
     !↵
    0.07
     Handy
    0.07
     ожид
    0.07
    Activations Density 0.029%

    No Known Activations