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. 97043
    Prev
    Next
    INDEX
    Explanations

    blood

    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
     geur
    -0.09
     renk
    -0.09
     indruk
    -0.08
    acay
    -0.08
    repen
    -0.08
     kleurr
    -0.08
    axy
    -0.07
    �
    -0.07
    asyon
    -0.07
    ッピング
    -0.07
    POSITIVE LOGITS
     заболевания
    0.10
    疾病
    0.09
     заболеваний
    0.09
     disease
    0.09
     emergencies
    0.09
     diseases
    0.09
     dysfunction
    0.09
     الأمراض
    0.08
    �
    0.08
     заболев
    0.08
    Activations Density 0.003%

    No Known Activations