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. 56006
    Prev
    Next
    INDEX
    Explanations

    RAW

    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
     achieves
    -0.08
     Katzen
    -0.08
     revolving
    -0.07
     Wall
    -0.07
     Quiz
    -0.07
     Break
    -0.07
    壁
    -0.07
    Barrier
    -0.07
    ่านั้น
    -0.07
     break
    -0.07
    POSITIVE LOGITS
    .raw
    0.12
    (raw
    0.11
     RAW
    0.11
     raw
    0.10
    raw
    0.09
     transformations
    0.09
    	raw
    0.09
    RAW
    0.09
    /raw
    0.09
     Lightroom
    0.09
    Activations Density 0.006%

    No Known Activations