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. 11-RESID-POST-AA
    6. 75933
    Prev
    Next
    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     всё
    -0.08
     metr
    -0.08
     objects
    -0.07
     ngg
    -0.07
     circumstances
    -0.07
     ty
    -0.07
     peg
    -0.07
     prévue
    -0.07
    issued
    -0.07
     vous
    -0.07
    POSITIVE LOGITS
    .verify
    0.09
    .writerow
    0.08
    مالك
    0.08
    .detect
    0.08
     Lana
    0.08
    Recognition
    0.08
     commerciële
    0.08
    ارن
    0.08
    _checksum
    0.08
     recognizing
    0.07
    Activations Density 0.000%

    No Known Activations