© 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. 23-RESID-POST-AA
    11. 6124
    Prev
    Next
    INDEX
    Explanations

    S

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    552
    -0.09
     உயிர
    -0.08
     પત્ન
    -0.08
    陪
    -0.08
    554
    -0.08
    322
    -0.08
     utrolig
    -0.08
    792
    -0.08
    926
    -0.08
     छह
    -0.08
    POSITIVE LOGITS
    ikh
    0.11
    ufi
    0.10
    uf
    0.09
     Korean
    0.08
    atso
    0.08
    inti
    0.08
    init
    0.08
    á
    0.08
     Asian
    0.08
    _inter
    0.08
    Activations Density 0.005%

    No Known Activations