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. 44793
    Prev
    Next
    INDEX
    Explanations

    olar

    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
    护
    -0.09
    نسي
    -0.08
     degrad
    -0.08
     Pl
    -0.08
    挡
    -0.07
    ربي
    -0.07
     respectivas
    -0.07
     pater
    -0.07
    र्थ
    -0.07
    ymes
    -0.07
    POSITIVE LOGITS
     bipolar
    0.08
     oscill
    0.08
    Script
    0.08
    Fac
    0.08
    artig
    0.08
    _fac
    0.08
     fueled
    0.07
     exhilar
    0.07
     schizophrenia
    0.07
     Stadt
    0.07
    Activations Density 0.002%

    No Known Activations