© 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. 30994
    Prev
    Next
    INDEX
    Explanations

    verted

    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
     spies
    -0.08
     Payments
    -0.08
    рева
    -0.08
     información
    -0.08
     eje
    -0.08
     Treasurer
    -0.08
    edwe
    -0.07
     рук
    -0.07
     choke
    -0.07
     apunt
    -0.07
    POSITIVE LOGITS
     personalities
    0.13
     personality
    0.13
     personalidade
    0.11
     personnalité
    0.11
     personalidad
    0.10
     Personality
    0.10
     વ્યક્ત
    0.10
     tarz
    0.09
    FLT
    0.09
    人格
    0.09
    Activations Density 0.004%

    No Known Activations