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. 119739
    Prev
    Next
    INDEX
    Explanations

    personal relationships

    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
     caut
    -0.08
     চিকিৎস
    -0.08
     behandelt
    -0.08
     đa
    -0.08
     hired
    -0.07
     돌
    -0.07
     மருத்துவ
    -0.07
     Rings
    -0.07
     선정
    -0.07
     rings
    -0.07
    POSITIVE LOGITS
     الصلاة
    0.10
     ferv
    0.10
     oración
    0.09
     devotion
    0.09
     Бога
    0.09
     personnelle
    0.09
     интенсив
    0.09
     personalize
    0.09
     intense
    0.09
     ощущения
    0.08
    Activations Density 0.055%

    No Known Activations