© 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. 3-RESID-POST-AA
    11. 2950
    Prev
    Next
    INDEX
    Explanations

    удар

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лений
    -0.08
    awl
    -0.08
     Rang
    -0.08
    NECTION
    -0.08
    .au
    -0.08
     Lees
    -0.07
     atal
    -0.07
     व्यवस्था
    -0.07
    ரை
    -0.07
     intending
    -0.07
    POSITIVE LOGITS
     Effective
    0.08
     benut
    0.08
     البحث
    0.07
    ್ರೆ
    0.07
     menn
    0.07
     PL
    0.07
     �
    0.07
     efectivos
    0.07
    exp
    0.07
    857
    0.07
    Activations Density 0.001%

    No Known Activations