Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19519
    Prev
    Next
    INDEX
    Explanations

    broke

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vert
    -0.08
     உருவ
    -0.07
     రూపొంద
    -0.07
     published
    -0.07
    -0.07
    scatter
    -0.07
    ుగు
    -0.07
     price
    -0.07
    iman
    -0.07
     вс
    -0.07
    POSITIVE LOGITS
    ㅋㅋ
    0.10
    зер
    0.09
     لدي
    0.09
     nginx
    0.09
     NOK
    0.09
    znym
    0.08
    Naz
    0.08
    睡
    0.08
     خواب
    0.08
     ustedes
    0.08
    Activations Density 0.001%

    No Known Activations