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. 44038
    Prev
    Next
    INDEX
    Explanations

    time/space

    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
     男女
    -0.08
    男女
    -0.08
    Minecraft
    -0.08
     emissão
    -0.08
    �
    -0.08
    女生
    -0.08
    男性
    -0.08
    _SLEEP
    -0.07
     అధికార
    -0.07
    官
    -0.07
    POSITIVE LOGITS
     plaintext
    0.10
    ात
    0.08
    plaintext
    0.08
     Oral
    0.07
     में
    0.07
     oral
    0.07
     zás
    0.07
     orally
    0.07
     직
    0.07
     orale
    0.07
    Activations Density 0.004%

    No Known Activations