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. 3-RESID-POST-AA
    6. 2205
    Prev
    Next
    INDEX
    Explanations

    twe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Perf
    -0.10
     Perf
    -0.09
    Gy
    -0.07
     Pan
    -0.07
     PF
    -0.07
    Ve
    -0.07
    Cer
    -0.07
    PH
    -0.07
     PH
    -0.07
    (exec
    -0.07
    POSITIVE LOGITS
     Illustrator
    0.07
     juniors
    0.07
     spotting
    0.07
     spy
    0.07
     Mink
    0.07
    停
    0.07
     haw
    0.07
     লাগে
    0.07
     nug
    0.07
     �
    0.07
    Activations Density 0.002%

    No Known Activations