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. 60955
    Prev
    Next
    INDEX
    Explanations

    statutes of limitations

    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
     පි
    -0.09
    ppu
    -0.08
     derrière
    -0.08
     samuti
    -0.08
     پشت
    -0.08
    Aan
    -0.08
     aproxima
    -0.08
    ’importe
    -0.08
     Aan
    -0.08
     فاص
    -0.08
    POSITIVE LOGITS
     exhaustive
    0.08
     sentences
    0.07
     Sent
    0.07
     tür
    0.07
     sentence
    0.07
     έναν
    0.07
     bar
    0.07
     dağı
    0.07
    (":
    0.07
     expensive
    0.07
    Activations Density 0.003%

    No Known Activations