© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    technical pages/documents

    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
     Perr
    -0.09
     outs
    -0.08
     Lippen
    -0.08
     improbable
    -0.07
    urio
    -0.07
     intoler
    -0.07
    clock
    -0.07
    law
    -0.07
     Rup
    -0.07
    -coded
    -0.07
    POSITIVE LOGITS
     页
    0.09
     �
    0.08
    /full
    0.08
    页
    0.08
     الدراسي
    0.08
     تقدم
    0.08
     fram
    0.08
     посвящ
    0.08
     дод
    0.08
     fragmentation
    0.08
    Activations Density 0.053%

    No Known Activations