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. 97106
    Prev
    Next
    INDEX
    Explanations

    unknown token

    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
    	i
    -0.08
    )i
    -0.08
     enqu
    -0.07
     apariencia
    -0.07
     Tomb
    -0.07
    _Ext
    -0.07
     rite
    -0.07
    ាញ
    -0.07
     hyst
    -0.07
     pum
    -0.07
    POSITIVE LOGITS
    �
    0.09
     Listing
    0.08
    LAY
    0.07
    .Of
    0.07
    披
    0.07
     Alberto
    0.07
    Larry
    0.07
    ault
    0.07
     Zal
    0.07
    _VISIBLE
    0.07
    Activations Density 0.000%

    No Known Activations