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. 130951
    Prev
    Next
    INDEX
    Explanations

    non-English 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
    creating
    -0.08
     ammonia
    -0.08
     centrifugal
    -0.08
     goû
    -0.08
     friction
    -0.07
     erf
    -0.07
    rt
    -0.07
     αποφ
    -0.07
    ánh
    -0.07
    acct
    -0.07
    POSITIVE LOGITS
    KEN
    0.09
    dığı
    0.09
    �
    0.08
    ulare
    0.08
    かな
    0.08
    	UINT
    0.08
    kning
    0.08
    uku
    0.08
    كبر
    0.08
     concerned
    0.08
    Activations Density 0.000%

    No Known Activations