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. 103921
    Prev
    Next
    INDEX
    Explanations

    Nikon

    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
     eas
    -0.08
    Fee
    -0.08
    lcool
    -0.08
     Lip
    -0.08
    Populate
    -0.08
     intoxic
    -0.08
    จังหวัด
    -0.08
    Declare
    -0.08
     الاتفاق
    -0.07
    Unable
    -0.07
    POSITIVE LOGITS
     DSLR
    0.12
     shotgun
    0.10
     Nikon
    0.10
     shot
    0.10
     Leica
    0.10
     HDR
    0.09
     Photography
    0.09
     vintage
    0.09
    摄影
    0.09
     Sony
    0.09
    Activations Density 0.065%

    No Known Activations