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. 98353
    Prev
    Next
    INDEX
    Explanations

    non-English and code

    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
     nightly
    -0.08
     dark
    -0.08
    /full
    -0.08
    _rotation
    -0.08
     diluted
    -0.07
    Rotation
    -0.07
     polymer
    -0.07
     inuu
    -0.07
    _dark
    -0.07
    dark
    -0.07
    POSITIVE LOGITS
    itur
    0.10
     команд
    0.08
    ทีม
    0.08
     Schnitt
    0.07
    یتی
    0.07
     HRESULT
    0.07
     pecho
    0.07
    ニュ
    0.07
     Greek
    0.07
    appoint
    0.07
    Activations Density 0.000%

    No Known Activations