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. 19165
    Prev
    Next
    INDEX
    Explanations

    Microsoft documentation and 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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <table
    -0.07
    &a
    -0.07
    -a
    -0.07
     retreats
    -0.07
     interesa
    -0.07
    /Table
    -0.07
     fi
    -0.07
     ibis
    -0.07
    &i
    -0.07
    &m
    -0.07
    POSITIVE LOGITS
     gånger
    0.08
     connex
    0.08
    .Generate
    0.08
     razy
    0.08
    .Connect
    0.08
    sdk
    0.08
     bäst
    0.08
     conex
    0.08
    ($"
    0.08
    _CONNECTION
    0.08
    Activations Density 0.001%

    No Known Activations