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. 60665
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    loin
    -0.08
     भूमिका
    -0.08
     स्पष्ट
    -0.08
     references
    -0.08
    ina
    -0.07
     lado
    -0.07
     Refer
    -0.07
     curated
    -0.07
    .Line
    -0.07
    미
    -0.07
    POSITIVE LOGITS
     updating
    0.10
     decrement
    0.09
     rollover
    0.09
    	update
    0.09
     amort
    0.09
    increment
    0.09
    Updating
    0.09
     overflowing
    0.09
    overflow
    0.09
     atualizar
    0.08
    Activations Density 0.006%

    No Known Activations