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. 76334
    Prev
    Next
    INDEX
    Explanations

    writing requests

    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
    वान
    -0.09
     फरवरी
    -0.08
     मिश्र
    -0.08
     gehand
    -0.08
     rightly
    -0.08
     הדברים
    -0.08
     Libert
    -0.08
    êmica
    -0.07
    endra
    -0.07
    _workers
    -0.07
    POSITIVE LOGITS
     rédaction
    0.08
     pretending
    0.08
     pret
    0.08
     bagi
    0.08
     generation
    0.07
     બનાવ
    0.07
     drafting
    0.07
     Hamlet
    0.07
     tale
    0.07
    Super
    0.07
    Activations Density 0.014%

    No Known Activations