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. 102653
    Prev
    Next
    INDEX
    Explanations

    width

    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
    390
    -0.07
    Pile
    -0.07
     Pi
    -0.07
    Configuration
    -0.07
     Ili
    -0.07
     फै
    -0.07
    oki
    -0.07
    Pand
    -0.07
    .Keyword
    -0.06
     retirement
    -0.06
    POSITIVE LOGITS
     tinder
    0.08
     зав
    0.08
    (figsize
    0.08
    ,height
    0.08
    َع
    0.08
    %;↵
    0.08
    contain
    0.08
    бав
    0.08
    _like
    0.08
     너
    0.08
    Activations Density 0.002%

    No Known Activations