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. 3-RESID-POST-AA
    6. 12508
    Prev
    Next
    INDEX
    Explanations

    swallowed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paleo
    -0.08
     Libro
    -0.08
     wok
    -0.08
     Hoch
    -0.07
     pancre
    -0.07
     پو
    -0.07
     komb
    -0.07
    (Code
    -0.07
     Hod
    -0.07
     trên
    -0.07
    POSITIVE LOGITS
    orp
    0.07
    úl
    0.07
     lieber
    0.07
     prayer
    0.07
     постав
    0.07
     ls
    0.07
    icide
    0.06
     மூ
    0.06
    ्यता
    0.06
     modem
    0.06
    Activations Density 0.003%

    No Known Activations