© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95869
    Prev
    Next
    INDEX
    Explanations

    problem solving

    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
     స్వ
    -0.09
     Gonz
    -0.08
    naj
    -0.08
     ................................................................
    -0.07
     Cen
    -0.07
     Instituto
    -0.07
     Github
    -0.07
     ಸ್ವ
    -0.07
     ases
    -0.07
     roz
    -0.07
    POSITIVE LOGITS
    Acknowled
    0.08
    expected
    0.08
    Knowing
    0.08
    (expected
    0.08
    Assembly
    0.08
    Definitely
    0.08
    Yes
    0.08
    Bullet
    0.08
    Routine
    0.08
    Lei
    0.07
    Activations Density 0.071%

    No Known Activations