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. 53073
    Prev
    Next
    INDEX
    Explanations

    use

    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
     Calif
    -0.09
     کف
    -0.09
     Peninsula
    -0.08
     consciente
    -0.08
     وتس
    -0.08
    BEN
    -0.08
     �
    -0.08
     رز
    -0.08
     ومن
    -0.08
     ره
    -0.08
    POSITIVE LOGITS
    _rule
    0.09
    _apply
    0.09
     rule
    0.09
    Rule
    0.08
    规则
    0.08
     Rule
    0.08
    тич
    0.08
     적용
    0.08
     aplicar
    0.08
     Litt
    0.08
    Activations Density 0.009%

    No Known Activations