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. 15-RESID-POST-AA
    6. 34
    Prev
    Next
    INDEX
    Explanations

    ми

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     zamanı
    -0.08
     lifetime
    -0.08
     procur
    -0.08
    leb
    -0.08
     typ
    -0.07
     √
    -0.07
     typen
    -0.07
     ty
    -0.07
    λήματα
    -0.07
    POSITIVE LOGITS
    想着
    0.09
    Can't
    0.09
    	function
    0.08
     revenge
    0.08
     Até
    0.08
    Até
    0.08
     continuam
    0.08
     Revenge
    0.08
    .Cascade
    0.08
    	User
    0.08
    Activations Density 0.016%

    No Known Activations