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. 97075
    Prev
    Next
    INDEX
    Explanations

    TRMM, GPM

    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
     ပြ
    -0.08
    fläche
    -0.08
     gepf
    -0.08
    002
    -0.08
     menopause
    -0.07
    sprechend
    -0.07
    .dead
    -0.07
    nergie
    -0.07
    gaard
    -0.07
     balan
    -0.07
    POSITIVE LOGITS
     এন
    0.07
    CMC
    0.07
     OM
    0.07
     lore
    0.07
     海
    0.07
     TOD
    0.07
     films
    0.07
     திரைப்பட
    0.07
     Dark
    0.07
    _logo
    0.07
    Activations Density 0.000%

    No Known Activations