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. 102851
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Were
    -0.07
    Be
    -0.07
    withdraw
    -0.07
     amel
    -0.07
    Sett
    -0.07
     opp
    -0.07
    Received
    -0.07
     requests
    -0.07
     выпуска
    -0.07
    etter
    -0.07
    POSITIVE LOGITS
    입니다
    0.10
    不能为空
    0.09
     번호
    0.09
    ,也是
    0.09
     것입니다
    0.09
     condensed
    0.08
     qq
    0.08
     enthält
    0.08
    路径
    0.08
    ,path
    0.08
    Activations Density 0.091%

    No Known Activations