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. 98228
    Prev
    Next
    INDEX
    Explanations

    it

    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
     vermitteln
    -0.09
    	rec
    -0.08
     Quadr
    -0.08
    ҳ
    -0.08
     Release
    -0.08
     recip
    -0.08
     qos
    -0.08
     Rec
    -0.08
    ब्र
    -0.07
     Trustees
    -0.07
    POSITIVE LOGITS
    -be
    0.09
    -R
    0.08
     consecu
    0.08
     mle
    0.07
    ara
    0.07
     defi
    0.07
     right
    0.07
    -ge
    0.07
    0.07
    ogen
    0.07
    Activations Density 0.025%

    No Known Activations