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. 12740
    Prev
    Next
    INDEX
    Explanations

    limitations and constraints

    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
    Brother
    -0.08
     meetup
    -0.08
     acclaimed
    -0.08
     apology
    -0.07
     dissertation
    -0.07
    删
    -0.07
     plagiarism
    -0.07
     六合
    -0.07
     hardcore
    -0.07
    与你
    -0.07
    POSITIVE LOGITS
     compens
    0.10
     eficaz
    0.10
     ions
    0.09
     Compensation
    0.09
     increases
    0.09
     증가
    0.09
     감소
    0.09
     компенса
    0.09
     �
    0.09
     advantageous
    0.09
    Activations Density 0.023%

    No Known Activations