Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 356
    Prev
    Next
    INDEX
    Explanations

    abortion and fetal viability

    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
     revolving
    -0.09
     의료
    -0.09
     hotline
    -0.09
     פת
    -0.08
     மருத்துவ
    -0.08
     криз
    -0.08
     Geschenk
    -0.08
     шту
    -0.08
     медицин
    -0.08
     Gifts
    -0.08
    POSITIVE LOGITS
     fuller
    0.08
     minimale
    0.08
     Serg
    0.08
     biết
    0.08
     Commit
    0.08
     filename
    0.08
     innocence
    0.08
    培养
    0.07
    ələ
    0.07
    filename
    0.07
    Activations Density 0.003%

    No Known Activations