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. 56222
    Prev
    Next
    INDEX
    Explanations

    would

    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
     Several
    -0.10
     Initial
    -0.09
    Initial
    -0.09
     Changed
    -0.09
    此次
    -0.08
    今回は
    -0.08
     Plusieurs
    -0.08
     You've
    -0.08
    Several
    -0.08
    btn
    -0.08
    POSITIVE LOGITS
    마다
    0.12
     oluyor
    0.10
     predictable
    0.09
    곤
    0.09
     olt
    0.08
    ็น
    0.08
     trips
    0.08
     whenever
    0.08
     telkens
    0.08
    ങ്ങളിൽ
    0.08
    Activations Density 0.132%

    No Known Activations