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. 49019
    Prev
    Next
    INDEX
    Explanations

    redirect

    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
     Tooth
    -0.08
    cule
    -0.08
     anten
    -0.07
    �
    -0.07
     Assurance
    -0.07
     Hewlett
    -0.07
     Clinton
    -0.07
    掌
    -0.07
     Ante
    -0.07
    灾
    -0.07
    POSITIVE LOGITS
     redirects
    0.09
     hacía
    0.08
     chuyển
    0.08
     către
    0.08
    IGATION
    0.07
    (PR
    0.07
     KOM
    0.07
     สำหรับ
    0.07
     tới
    0.07
     למ
    0.07
    Activations Density 0.005%

    No Known Activations