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. 77549
    Prev
    Next
    INDEX
    Explanations

    Gravitational constant

    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
    -ce
    -0.09
    emming
    -0.08
     pronounce
    -0.08
     sinus
    -0.08
    Sr
    -0.07
    ungwa
    -0.07
    (一
    -0.07
     deriva
    -0.07
     шы
    -0.07
     bagu
    -0.07
    POSITIVE LOGITS
     viruses
    0.08
     mortgages
    0.08
     Jesus
    0.08
    othermal
    0.08
     agarr
    0.07
    jen
    0.07
     treaty
    0.07
     hant
    0.07
    jual
    0.07
    全民
    0.07
    Activations Density 0.002%

    No Known Activations