© 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. 44831
    Prev
    Next
    INDEX
    Explanations

    using

    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
    创业
    -0.09
     promis
    -0.08
    zicht
    -0.08
     Betracht
    -0.08
     salários
    -0.08
     рекон
    -0.08
     antrop
    -0.08
    گرام
    -0.08
     Newton
    -0.08
     lont
    -0.08
    POSITIVE LOGITS
    (hidden
    0.10
     hide
    0.10
    .hidden
    0.10
     fenced
    0.10
     conceal
    0.09
    _hide
    0.09
     hidden
    0.09
    .hide
    0.09
    hidden
    0.09
    Hide
    0.09
    Activations Density 0.003%

    No Known Activations