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. 97073
    Prev
    Next
    INDEX
    Explanations

    Log

    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
     Ò
    -0.09
     logarith
    -0.09
     modified
    -0.08
     общества
    -0.08
     OCT
    -0.08
     বিশ্বের
    -0.08
     로그인
    -0.08
     MOB
    -0.08
     πολύ
    -0.08
     লগ
    -0.08
    POSITIVE LOGITS
    shipping
    0.13
     shipping
    0.13
    stash
    0.13
    _shipping
    0.12
    Shipping
    0.12
     Shipping
    0.11
    back
    0.11
    gly
    0.11
    DNA
    0.10
    shuffle
    0.10
    Activations Density 0.002%

    No Known Activations