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. 11761
    Prev
    Next
    INDEX
    Explanations

    Dialogue and adverbs

    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
     interconnected
    -0.08
     Licence
    -0.07
     inverted
    -0.07
     власти
    -0.07
     Viol
    -0.07
    -0.07
     база
    -0.07
     личности
    -0.07
    ーナ
    -0.07
     imposing
    -0.07
    POSITIVE LOGITS
    .forward
    0.09
     voorzichtig
    0.08
    保护
    0.08
    _trial
    0.08
     dildo
    0.08
    �
    0.08
    其
    0.08
    손
    0.08
    .context
    0.08
     toilet
    0.08
    Activations Density 0.000%

    No Known Activations