© 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. 78372
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    >}
    -0.09
     popul
    -0.08
     leuk
    -0.08
    ระดับ
    -0.07
     locales
    -0.07
    >}↵
    -0.07
     Island
    -0.07
     episod
    -0.07
     dak
    -0.07
    õ
    -0.07
    POSITIVE LOGITS
     optimization
    0.11
     maximizing
    0.10
     maximize
    0.10
     minimizing
    0.10
     minimize
    0.10
    Optimization
    0.10
     optimize
    0.09
     optimizing
    0.09
    Optimize
    0.09
     Optimization
    0.09
    Activations Density 0.104%

    No Known Activations