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. 111569
    Prev
    Next
    INDEX
    Explanations

    �

    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
    .TYPE
    -0.08
    waren
    -0.08
    成绩
    -0.07
     cob
    -0.07
     Ron
    -0.07
     stroll
    -0.07
    .Editor
    -0.07
    -ist
    -0.07
     tom
    -0.07
    -->↵↵
    -0.07
    POSITIVE LOGITS
    صة
    0.09
     pula
    0.08
    ತ್ತರ
    0.07
     Pollution
    0.07
     Bucks
    0.07
    تر
    0.07
    ೇತ್ರ
    0.07
     النار
    0.07
     hil
    0.07
    tritt
    0.07
    Activations Density 0.001%

    No Known Activations