© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78959
    Prev
    Next
    INDEX
    Explanations

    action

    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
     beh
    -0.08
    /generated
    -0.07
     fract
    -0.07
     Cached
    -0.07
    opak
    -0.07
     aconsel
    -0.07
     rand
    -0.07
     impetus
    -0.07
    andidato
    -0.07
    	cache
    -0.07
    POSITIVE LOGITS
     enctype
    0.11
     POST
    0.10
    POST
    0.10
    .href
    0.10
     posting
    0.10
    ='/
    0.10
    .ajax
    0.10
     ajax
    0.10
     destinos
    0.10
     destino
    0.09
    Activations Density 0.004%

    No Known Activations