© 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. 54890
    Prev
    Next
    INDEX
    Explanations

    bounding box

    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
     difficult
    -0.09
     spins
    -0.09
     obliv
    -0.08
     Spins
    -0.08
     tingkat
    -0.07
     elabor
    -0.07
    -as
    -0.07
     올
    -0.07
     Copp
    -0.07
     architectures
    -0.07
    POSITIVE LOGITS
    :CGRect
    0.15
     CGRect
    0.11
    CGRect
    0.10
    柄
    0.10
     vena
    0.09
     QRect
    0.09
    angular
    0.09
    ifier
    0.09
     بندی
    0.09
    angles
    0.09
    Activations Density 0.004%

    No Known Activations