Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58678
    Prev
    Next
    INDEX
    Explanations

    need

    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
    -"
    -0.08
    rif
    -0.08
    наг
    -0.08
    serialization
    -0.08
    ไหม
    -0.07
     rodi
    -0.07
    tych
    -0.07
     hinter
    -0.07
    oue
    -0.07
     볼
    -0.07
    POSITIVE LOGITS
    Because
    0.08
     دقيقة
    0.08
     modulo
    0.08
     essentially
    0.08
     intuition
    0.08
     probable
    0.08
    Ultimately
    0.07
     Because
    0.07
     терп
    0.07
     handshake
    0.07
    Activations Density 0.086%

    No Known Activations