© 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. 7-RESID-POST-AA
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    score and full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     جلد
    -0.08
    'ar
    -0.08
    ’ar
    -0.08
    .dialog
    -0.08
    ški
    -0.08
    Facade
    -0.07
     Mein
    -0.07
    ler
    -0.07
     privadas
    -0.07
    $ar
    -0.07
    POSITIVE LOGITS
     Navi
    0.08
     chocol
    0.08
     hipot
    0.08
    �
    0.07
    -equ
    0.07
     Patty
    0.07
     ush
    0.07
     pro
    0.07
     equ
    0.07
    skraft
    0.07
    Activations Density 0.016%

    No Known Activations