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. 12651
    Prev
    Next
    INDEX
    Explanations

    codons

    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
     brand
    -0.09
     Brand
    -0.09
    Brand
    -0.09
    -brand
    -0.08
     Lake
    -0.08
     бренд
    -0.08
    .Brand
    -0.08
     fountain
    -0.08
     leveraged
    -0.07
     브랜드
    -0.07
    POSITIVE LOGITS
     ಮೂರು
    0.10
    three
    0.10
     তিন
    0.10
     paylines
    0.09
     nucleotide
    0.09
    _three
    0.09
     genes
    0.09
     трех
    0.09
     മൂന്ന്
    0.09
    长度
    0.09
    Activations Density 0.003%

    No Known Activations