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. 45329
    Prev
    Next
    INDEX
    Explanations

    papers

    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
    Enc
    -0.09
    -cont
    -0.08
    Small
    -0.08
    :{↵
    -0.07
    Reduced
    -0.07
    Additional
    -0.07
    anska
    -0.07
    '[
    -0.07
    -0.07
    -compatible
    -0.07
    POSITIVE LOGITS
     nhằm
    0.10
     посвящ
    0.10
     помогут
    0.08
     Som
    0.08
     нашей
    0.08
     hòa
    0.08
    旨
    0.07
     максимально
    0.07
     поможет
    0.07
     sd
    0.07
    Activations Density 0.034%

    No Known Activations