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. 113925
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    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
    _wrapper
    -0.08
     offender
    -0.08
     ciert
    -0.08
     Governor
    -0.07
     Graham
    -0.07
     Constitution
    -0.07
     Qualification
    -0.07
    см
    -0.07
     уголов
    -0.07
     действительно
    -0.07
    POSITIVE LOGITS
     watercolor
    0.10
     કલ
    0.09
     beside
    0.08
     textured
    0.08
    /icons
    0.08
    /png
    0.08
    摄影
    0.08
    ٢٠
    0.08
     kleurr
    0.08
    kee
    0.08
    Activations Density 0.075%

    No Known Activations