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. 46233
    Prev
    Next
    INDEX
    Explanations

    _device

    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
    atering
    -0.08
    UF
    -0.07
     양
    -0.07
     dense
    -0.07
    оритет
    -0.07
    oui
    -0.07
    dense
    -0.07
    =<
    -0.07
    ס
    -0.07
    анг
    -0.07
    POSITIVE LOGITS
    �
    0.08
     endl
    0.08
     piè
    0.08
     WAN
    0.08
     Bite
    0.07
    ürü
    0.07
    ్క
    0.07
    陷
    0.07
    峰
    0.07
     மூலம்
    0.07
    Activations Density 0.001%

    No Known Activations