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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51544
    Prev
    Next
    INDEX
    Explanations

    deriving/obtaining

    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
     increases
    -0.09
    increase
    -0.09
     vergroten
    -0.08
    take
    -0.08
     aumenta
    -0.08
    Managing
    -0.08
     aumentar
    -0.08
     gérer
    -0.08
     Encourage
    -0.08
    ಾನ್ಯ
    -0.08
    POSITIVE LOGITS
    得到
    0.28
    得
    0.24
     得
    0.23
     얻
    0.21
    推出
    0.20
     deriving
    0.19
     derive
    0.19
    获得
    0.19
     derives
    0.19
     получить
    0.18
    Activations Density 0.041%

    No Known Activations