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. 55449
    Prev
    Next
    INDEX
    Explanations

    abo

    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
     habitu
    -0.08
    اهي
    -0.08
    271
    -0.08
     DNI
    -0.08
    alty
    -0.07
    -head
    -0.07
    PLC
    -0.07
     anaer
    -0.07
     Caja
    -0.07
     tendon
    -0.07
    POSITIVE LOGITS
     Spending
    0.09
    _footer
    0.08
    _assert
    0.08
    Cull
    0.08
     Processor
    0.08
     TXT
    0.08
     бөл
    0.08
     Routed
    0.08
    】【
    0.07
     Finished
    0.07
    Activations Density 0.007%

    No Known Activations