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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18791
    Prev
    Next
    INDEX
    Explanations

    say ".create"

    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
     સપ
    -0.08
     सप
    -0.07
     knowledge
    -0.07
     Entity
    -0.07
     konkrete
    -0.07
     rêves
    -0.07
    knowledge
    -0.07
    .tools
    -0.07
     disciplines
    -0.07
     مشکلات
    -0.07
    POSITIVE LOGITS
     जोर
    0.09
    .rename
    0.09
    -_
    0.08
    テレビ
    0.08
    _Right
    0.08
     ugu
    0.08
     ук
    0.08
    rename
    0.08
     domést
    0.08
     bipartisan
    0.08
    Activations Density 0.004%

    No Known Activations