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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 12749
    Prev
    Next
    INDEX
    Explanations

    ear

    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
    -her
    -0.09
     Her
    -0.09
     HER
    -0.09
     Monte
    -0.08
    .her
    -0.08
    .arc
    -0.08
    jek
    -0.08
    .mouse
    -0.08
    /P
    -0.07
    her
    -0.07
    POSITIVE LOGITS
     qol
    0.09
     implants
    0.08
    0.08
    cassert
    0.08
    智能
    0.08
     olen
    0.08
    射
    0.08
    opleft
    0.08
     inteligente
    0.07
    /artificial
    0.07
    Activations Density 0.005%

    No Known Activations