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. 98445
    Prev
    Next
    INDEX
    Explanations

    Python code

    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
    =null
    -0.18
    =false
    -0.17
    ,//
    -0.16
    =true
    -0.16
    .*/↵
    -0.15
    ,false
    -0.15
    /{{$
    -0.15
    ");↵//
    -0.15
     {$
    -0.15
    *Math
    -0.15
    POSITIVE LOGITS
     isinstance
    0.34
    =None
    0.32
    _kwargs
    0.32
    (None
    0.31
     kwargs
    0.31
    =True
    0.31
    .py
    0.30
    =False
    0.30
     None
    0.30
     hasattr
    0.29
    Activations Density 0.645%

    No Known Activations