Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120167
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    来看
    -0.08
    astra
    -0.08
    /meta
    -0.07
    /context
    -0.07
    ERY
    -0.07
    hsil
    -0.07
    	ac
    -0.07
     göre
    -0.07
    ARIA
    -0.07
    aculture
    -0.07
    POSITIVE LOGITS
    وت
    0.08
     great
    0.08
     wors
    0.07
     are
    0.07
     Somos
    0.07
     worsening
    0.07
    (TAG
    0.07
     Tencent
    0.07
     Toch
    0.07
     sự
    0.07
    Activations Density 0.058%

    No Known Activations