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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1550
    Prev
    Next
    INDEX
    Explanations

    исключ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .prop
    -0.09
     oscuro
    -0.08
    mehr
    -0.08
     hil
    -0.08
    渡
    -0.08
     ра
    -0.08
     tarde
    -0.08
     millis
    -0.07
    -0.07
     incarn
    -0.07
    POSITIVE LOGITS
    Adj
    0.08
     com
    0.07
     cir
    0.07
    0.07
     चोरी
    0.07
     possibility
    0.07
     Regression
    0.06
     Dou
    0.06
     regression
    0.06
     Exceptions
    0.06
    Activations Density 0.002%

    No Known Activations