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. 74606
    Prev
    Next
    INDEX
    Explanations

    professor

    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
    .results
    -0.09
     결과
    -0.09
    返信
    -0.09
     परिणाम
    -0.08
     raffle
    -0.08
    irim
    -0.08
     pater
    -0.08
     freebies
    -0.08
     sonuç
    -0.08
     महामारी
    -0.08
    POSITIVE LOGITS
     exercício
    0.08
     hypothetical
    0.08
     ro
    0.08
     fett
    0.08
     speculative
    0.07
     בבית
    0.07
     rises
    0.07
     Emer
    0.07
     presso
    0.07
     แ
    0.07
    Activations Density 0.028%

    No Known Activations