© 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. 75537
    Prev
    Next
    INDEX
    Explanations

    Select

    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
     Heaven
    -0.08
    .Minute
    -0.08
    ’ag
    -0.08
     Denk
    -0.07
    -Min
    -0.07
     MVP
    -0.07
     TC
    -0.07
    متع
    -0.07
     Johansson
    -0.07
     ترین
    -0.07
    POSITIVE LOGITS
    92
    0.09
    98
    0.08
    Shared
    0.08
    抱
    0.08
    88
    0.08
    95
    0.08
    90
    0.08
     compart
    0.08
    chtest
    0.08
     Ansch
    0.07
    Activations Density 0.000%

    No Known Activations