© 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. 47108
    Prev
    Next
    INDEX
    Explanations

    file names

    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
     osserv
    -0.08
    ÍC
    -0.07
    ोस
    -0.07
     spawning
    -0.07
     Routing
    -0.07
    ò
    -0.07
    ően
    -0.07
     микро
    -0.07
     regexp
    -0.07
     pinch
    -0.07
    POSITIVE LOGITS
    ='/
    0.08
     말씀
    0.08
    _H
    0.08
    _saved
    0.08
    saved
    0.08
    Saved
    0.08
     kwestie
    0.08
    save
    0.08
     creation
    0.08
    ғай
    0.07
    Activations Density 0.000%

    No Known Activations