Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19387
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ]).↵
    -0.13
     nuest
    -0.12
    ].↵
    -0.11
    etõttu
    -0.10
    iloeng
    -0.10
    nehin
    -0.10
     росс
    -0.10
    ancetype
    -0.10
    'ezie
    -0.10
    iciembre
    -0.10
    POSITIVE LOGITS
     \(
    0.09
     (\
    0.09
    :**
    0.09
     -
    0.08
    :
    0.08
    :「
    0.08
     (**
    0.08
    :↵↵
    0.08
     ()↵↵
    0.07
    :
    0.07
    Activations Density 0.128%

    No Known Activations