© 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. 19-RESID-POST-AA
    11. 102723
    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ihe
    -0.08
    ीय
    -0.08
    iera
    -0.08
    umela
    -0.08
    elike
    -0.07
    mester
    -0.07
    ématique
    -0.07
    agues
    -0.07
     afore
    -0.07
    íst
    -0.07
    POSITIVE LOGITS
    рым
    0.11
    рые
    0.10
    ойчив
    0.09
    атков
    0.09
    ყვეტ
    0.09
    צן
    0.09
    упить
    0.09
    рый
    0.09
    рыма
    0.09
    риж
    0.09
    Activations Density 0.003%

    No Known Activations