Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98609
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ίδια
    -0.09
    zelfde
    -0.08
     metals
    -0.08
     μαζί
    -0.08
     caminos
    -0.08
    Actions
    -0.08
     magnets
    -0.08
     trees
    -0.08
     books
    -0.08
    Modules
    -0.08
    POSITIVE LOGITS
    	the
    0.10
    	The
    0.10
     The
    0.09
     the
    0.09
    the
    0.08
    geist
    0.08
     THE
    0.08
    .the
    0.08
     Gareth
    0.08
    >The
    0.08
    Activations Density 0.005%

    No Known Activations