Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 95135
    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
     secrets
    -0.08
     therefore
    -0.07
     समस्या
    -0.07
     infection
    -0.07
     HB
    -0.07
     समस्य
    -0.07
    คือ
    -0.07
     विज्ञान
    -0.07
    .ibm
    -0.07
     princesa
    -0.07
    POSITIVE LOGITS
     Ayn
    0.09
     Spoken
    0.09
     halt
    0.09
     Einst
    0.08
    旗下
    0.08
     toppen
    0.08
     lil
    0.08
     рядом
    0.08
     العصر
    0.08
    紙
    0.08
    Activations Density 0.007%

    No Known Activations