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. 130944
    Prev
    Next
    INDEX
    Explanations

    Multilingual text

    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
    R
    -0.08
     super
    -0.08
    -Se
    -0.08
    762
    -0.08
    gew
    -0.08
    786
    -0.08
    Roy
    -0.08
     R
    -0.08
     rect
    -0.07
    -0.07
    POSITIVE LOGITS
     shaved
    0.08
     број
    0.08
    _Reset
    0.08
    apeut
    0.08
     resets
    0.08
     اعت
    0.08
     RESET
    0.08
    _oct
    0.08
    CCCC
    0.08
    RESET
    0.08
    Activations Density 0.009%

    No Known Activations