© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    пон

    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
    036
    -0.08
    fora
    -0.07
    ullen
    -0.07
    umann
    -0.07
    unt
    -0.07
    Ips
    -0.07
    _pd
    -0.07
    IPL
    -0.07
    utab
    -0.07
    _pol
    -0.07
    POSITIVE LOGITS
     hmm
    0.08
    态
    0.08
     Cher
    0.07
     geology
    0.07
     crem
    0.07
    观察
    0.07
     unterstützt
    0.07
     lol
    0.07
    则
    0.07
    verständlich
    0.07
    Activations Density 0.001%

    No Known Activations