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. 130745
    Prev
    Next
    INDEX
    Explanations

    Calculations

    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
    enue
    -0.09
    str
    -0.08
    .vi
    -0.08
    enthal
    -0.08
     sul
    -0.07
    ulte
    -0.07
    _mu
    -0.07
    gu
    -0.07
    -0.07
    _MI
    -0.07
    POSITIVE LOGITS
     Segment
    0.08
    unang
    0.07
     Peer
    0.07
     abbreviation
    0.07
     oto
    0.07
     shampoo
    0.07
     unic
    0.07
    TH
    0.07
    ंजन
    0.07
    hlah
    0.07
    Activations Density 0.026%

    No Known Activations