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. 77172
    Prev
    Next
    INDEX
    Explanations

    Mysterious incidents

    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
    207
    -0.08
     probes
    -0.08
    Lek
    -0.08
    ର
    -0.07
     Le
    -0.07
    jeri
    -0.07
    208
    -0.07
     Raf
    -0.07
     picker
    -0.07
     Lek
    -0.07
    POSITIVE LOGITS
     falou
    0.09
     anod
    0.08
     einmal
    0.08
     פעם
    0.08
     annuelle
    0.08
    વણી
    0.08
     accueill
    0.08
     אן
    0.08
     angegeben
    0.08
     Erwart
    0.08
    Activations Density 0.000%

    No Known Activations