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. 98202
    Prev
    Next
    INDEX
    Explanations

    col

    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
     shr
    -0.08
    -0.07
    جاز
    -0.07
    lie
    -0.07
    hren
    -0.07
    Shr
    -0.07
    予
    -0.07
     opcion
    -0.07
    ss
    -0.07
     sobie
    -0.07
    POSITIVE LOGITS
    esco
    0.08
    аў
    0.08
     join
    0.08
    бач
    0.08
     төс
    0.07
    кил
    0.07
     VALUES
    0.07
    айте
    0.07
    ёл
    0.07
    	boost
    0.07
    Activations Density 0.000%

    No Known Activations