© 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 EvalsExportsAPI 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. 50185
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
     केला
    -0.15
     झाला
    -0.13
     ktorý
    -0.13
     быў
    -0.13
     который
    -0.13
     který
    -0.13
     был
    -0.12
     був
    -0.12
     કર્યો
    -0.12
     आला
    -0.12
    POSITIVE LOGITS
    ител
    0.10
    ен
    0.09
    ЕН
    0.09
    하다
    0.09
    тен
    0.08
    есс
    0.08
    ਿਹ
    0.08
    —all
    0.08
    им
    0.08
    ател
    0.08
    Activations Density 0.004%

    No Known Activations