© 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. 12961
    Prev
    Next
    INDEX
    Explanations

    echo

    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
    Kal
    -0.08
     Universe
    -0.07
     نفس
    -0.07
     Ethi
    -0.07
     mostly
    -0.07
    ,value
    -0.07
     Кит
    -0.07
     një
    -0.07
    etection
    -0.07
     Strip
    -0.07
    POSITIVE LOGITS
     decid
    0.08
     pico
    0.08
    票
    0.08
     टिकट
    0.08
     elk
    0.08
     hipotec
    0.08
     audible
    0.08
    熊
    0.08
     bonnet
    0.07
    konto
    0.07
    Activations Density 0.000%

    No Known Activations