© 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. 11-RESID-POST-AA
    11. 29729
    Prev
    Next
    INDEX
    Explanations

    Word fragments and affixes

    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
     Helping
    -0.09
    Helping
    -0.08
    ellingen
    -0.08
    reiro
    -0.08
     rollout
    -0.08
    baby
    -0.08
     billig
    -0.08
    ীদ
    -0.07
     kurz
    -0.07
    据
    -0.07
    POSITIVE LOGITS
    otics
    0.08
     aph
    0.08
    ophobia
    0.08
     cringe
    0.08
    odont
    0.08
     couple
    0.08
    pathy
    0.08
    ´
    0.08
     pale
    0.08
     abyss
    0.08
    Activations Density 0.145%

    No Known Activations