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. 65857
    Prev
    Next
    INDEX
    Explanations

    Women

    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
     spontaneous
    -0.07
     ear
    -0.07
    itoy
    -0.07
     дав
    -0.07
    obora
    -0.07
     PTA
    -0.07
     matcher
    -0.06
     attributable
    -0.06
     Ner
    -0.06
     HUD
    -0.06
    POSITIVE LOGITS
     Evelyn
    0.09
    🏼
    0.09
    们
    0.08
     Sall
    0.08
    ့
    0.08
     adm
    0.08
     Rost
    0.07
    naire
    0.07
    伟
    0.07
     cath
    0.07
    Activations Density 0.042%

    No Known Activations