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. 11-RESID-POST-AA
    6. 12173
    Prev
    Next
    INDEX
    Explanations

    "where possible"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prepar
    -0.08
    941
    -0.08
    .Future
    -0.07
    ચ્ચ
    -0.07
    ’a
    -0.07
     dedic
    -0.07
     funds
    -0.07
    582
    -0.07
     Prepar
    -0.07
    ири
    -0.07
    POSITIVE LOGITS
     जहां
    0.10
     wherever
    0.10
    sicht
    0.09
     случа
    0.08
     khona
    0.08
    езде
    0.08
     যেখানে
    0.08
    地方
    0.08
     случаях
    0.08
     flatter
    0.08
    Activations Density 0.032%

    No Known Activations