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. 58880
    Prev
    Next
    INDEX
    Explanations

    patrolling

    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
    forth
    -0.07
     Poor
    -0.07
     Evan
    -0.07
     magical
    -0.07
     superviv
    -0.07
     withstand
    -0.07
     económicos
    -0.07
     packaging
    -0.07
    �
    -0.07
     tratados
    -0.07
    POSITIVE LOGITS
     patrol
    0.12
     roam
    0.10
    巡视
    0.09
     vigilant
    0.09
     roaming
    0.09
     вооруж
    0.08
     scans
    0.08
     stationed
    0.08
     mens
    0.08
     duty
    0.08
    Activations Density 0.005%

    No Known Activations