© 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. 94869
    Prev
    Next
    INDEX
    Explanations

    выс

    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
     tuna
    -0.08
    orca
    -0.08
    GA
    -0.08
    ussat
    -0.07
     rése
    -0.07
    üten
    -0.07
    /preferences
    -0.07
    vec
    -0.07
     personals
    -0.07
     unh
    -0.07
    POSITIVE LOGITS
    idot
    0.08
    .nil
    0.08
    nid
    0.08
    .present
    0.08
     logr
    0.07
     стро
    0.07
     née
    0.07
     системы
    0.07
     relatives
    0.07
     системой
    0.07
    Activations Density 0.001%

    No Known Activations