© 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. 3-RESID-POST-AA
    11. 2789
    Prev
    Next
    INDEX
    Explanations

    California

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ν
    -0.07
    044
    -0.07
    atag
    -0.07
    .unsqueeze
    -0.07
    Saturday
    -0.07
    枝
    -0.07
    ikum
    -0.07
     disco
    -0.07
    가능
    -0.07
    ɛ
    -0.07
    POSITIVE LOGITS
     मिश
    0.08
     continua
    0.08
     Mission
    0.08
    Ov
    0.07
     Continua
    0.07
     :)↵↵
    0.07
    Mig
    0.07
     Mira
    0.07
     atos
    0.07
     mysteries
    0.07
    Activations Density 0.001%

    No Known Activations