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. 12529
    Prev
    Next
    INDEX
    Explanations

    carrot cake recipes

    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
     NOS
    -0.08
    أس
    -0.07
     müsse
    -0.07
    NOS
    -0.07
     besuchen
    -0.07
     Scandin
    -0.07
    идан
    -0.07
    .Resolve
    -0.07
     perde
    -0.07
     Homo
    -0.07
    POSITIVE LOGITS
    ypass
    0.08
    考试
    0.08
    carry
    0.08
    smith
    0.08
    hat
    0.08
    .shape
    0.08
    laap
    0.08
     sunn
    0.07
    qrst
    0.07
    ók
    0.07
    Activations Density 0.006%

    No Known Activations