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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106206
    Prev
    Next
    INDEX
    Explanations

    any one

    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
     Bela
    -0.10
    骗人
    -0.08
    ások
    -0.08
     supplemented
    -0.08
     monnaie
    -0.08
    bic
    -0.07
     Burger
    -0.07
    urgical
    -0.07
     효과
    -0.07
    _HAND
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.08
    0.08
    เลย
    0.08
     mena
    0.08
     sensed
    0.08
     slightest
    0.08
    라도
    0.08
     collective
    0.07
    0.07
     underlying
    0.07
    Activations Density 0.024%

    No Known Activations