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. 296
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    !!!↵
    -0.09
    ORIES
    -0.08
     !!↵
    -0.08
     собой
    -0.08
    是真的
    -0.08
    ℃↵
    -0.08
    高潮
    -0.08
     밝�
    -0.08
     أهم
    -0.08
    세계
    -0.08
    POSITIVE LOGITS
     Anda
    0.08
     ao
    0.08
     nop
    0.07
     Woo
    0.07
     pretty
    0.07
     likelihood
    0.07
    areness
    0.07
     Azure
    0.07
     likely
    0.07
    ив
    0.07
    Activations Density 0.084%

    No Known Activations