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. 9111
    Prev
    Next
    INDEX
    Explanations

    if

    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
    。所以
    -0.09
     Betracht
    -0.09
    "></
    -0.09
     acreage
    -0.08
     hence
    -0.08
    ]]
    -0.08
     visc
    -0.08
    ???↵↵
    -0.08
     연
    -0.07
     iid
    -0.07
    POSITIVE LOGITS
     scammers
    0.09
     Bird
    0.08
     Las
    0.08
    कि
    0.07
    Exper
    0.07
     Jelly
    0.07
    Las
    0.07
     pamp
    0.07
     Jeremy
    0.07
     disparity
    0.07
    Activations Density 0.035%

    No Known Activations