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. 98289
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    ^
    -0.09
    λές
    -0.09
     centimeters
    -0.09
     pointers
    -0.09
    ++,
    -0.09
    ^)
    -0.09
    -leading
    -0.08
     _,
    -0.08
    -',
    -0.08
     €,
    -0.08
    POSITIVE LOGITS
     OF
    0.10
    OF
    0.09
     Dentro
    0.08
    _OF
    0.08
    _of
    0.08
    .of
    0.08
    Dentro
    0.08
     Confidence
    0.08
    within
    0.07
     Uphol
    0.07
    Activations Density 0.016%

    No Known Activations