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. 76349
    Prev
    Next
    INDEX
    Explanations

    upright

    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
     negoc
    -0.08
     OE
    -0.07
    neg
    -0.07
     규모
    -0.07
     effectively
    -0.07
     neg
    -0.07
     shedding
    -0.07
     shed
    -0.07
     sheds
    -0.07
     niew
    -0.07
    POSITIVE LOGITS
    -benar
    0.09
    ienta
    0.08
     прили
    0.08
    yty
    0.08
    =format
    0.08
     Assembleia
    0.08
     vif
    0.08
     ajal
    0.07
     Upr
    0.07
    _pg
    0.07
    Activations Density 0.004%

    No Known Activations