© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18222
    Prev
    Next
    INDEX
    Explanations

    a

    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
     ضروری
    -0.11
    ature
    -0.09
     erforder
    -0.09
     requisite
    -0.09
     필요한
    -0.09
     اللازمة
    -0.09
     જરૂરી
    -0.09
     necesarios
    -0.09
     необходимых
    -0.08
     неабход
    -0.08
    POSITIVE LOGITS
     answer
    0.17
    答案
    0.16
     answers
    0.15
     उत्तर
    0.14
    Answer
    0.14
     antwoord
    0.14
    回答
    0.14
    answer
    0.13
     ಉತ್ತರ
    0.13
     ответа
    0.13
    Activations Density 0.050%

    No Known Activations