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. 56092
    Prev
    Next
    INDEX
    Explanations

    exposition

    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
     lions
    -0.10
     validate
    -0.08
     kopen
    -0.08
     Lind
    -0.07
     lucrative
    -0.07
     isolated
    -0.07
     ખરી
    -0.07
     møte
    -0.07
     moč
    -0.07
     కొన
    -0.07
    POSITIVE LOGITS
     deck
    0.09
     과정
    0.09
     deeds
    0.08
    /story
    0.08
    arbeit
    0.08
    대로
    0.08
    DUCTION
    0.08
     बातें
    0.08
    affer
    0.08
    时期
    0.08
    Activations Density 0.004%

    No Known Activations