© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2677
    Prev
    Next
    INDEX
    Explanations

    Content

    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
     Ani
    -0.08
     NT
    -0.08
     NS
    -0.08
     respon
    -0.08
     teste
    -0.08
    edt
    -0.07
     Idle
    -0.07
     stuffing
    -0.07
    out
    -0.07
     OSX
    -0.07
    POSITIVE LOGITS
     fortalecer
    0.07
    Multiplicity
    0.07
     feared
    0.07
    ત્ર
    0.07
    වර
    0.07
    (bundle
    0.07
     gears
    0.07
     aggrav
    0.07
    とな
    0.07
    odob
    0.07
    Activations Density 0.001%

    No Known Activations