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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48068
    Prev
    Next
    INDEX
    Explanations

    head rotation/eyesight

    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
    上
    -0.08
     respectful
    -0.08
    征
    -0.08
     التجاري
    -0.07
    Dish
    -0.07
    fy
    -0.07
     lined
    -0.07
     WR
    -0.07
     declining
    -0.07
    antec
    -0.07
    POSITIVE LOGITS
     Fähigkeit
    0.11
     Ability
    0.10
     способен
    0.10
     graças
    0.10
     Благодаря
    0.10
     способность
    0.10
     способны
    0.10
     kemampuan
    0.09
     grâce
    0.09
     Dankzij
    0.09
    Activations Density 0.008%

    No Known Activations