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. 87981
    Prev
    Next
    INDEX
    Explanations

    exemption

    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
    拾
    -0.08
    عيد
    -0.08
    lle
    -0.08
    خير
    -0.08
     Aure
    -0.08
    Encoded
    -0.07
     Mega
    -0.07
     boy
    -0.07
    円
    -0.07
    mega
    -0.07
    POSITIVE LOGITS
    掉
    0.09
     exemptions
    0.09
     Qualifications
    0.09
     qualifications
    0.09
     waived
    0.08
     undue
    0.08
     ratione
    0.08
     Qualification
    0.08
     khỏi
    0.08
     exemption
    0.08
    Activations Density 0.009%

    No Known Activations