© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103487
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     مناطق
    -0.10
     فساد
    -0.09
    ್ವಹ
    -0.09
     المناطق
    -0.09
     ظلم
    -0.08
     tüm
    -0.08
     scandals
    -0.08
    벽
    -0.08
     corrupted
    -0.08
     تأثير
    -0.08
    POSITIVE LOGITS
     informative
    0.17
     explanatory
    0.15
     helpful
    0.15
     academic
    0.14
     supportive
    0.14
     educ
    0.13
     instructional
    0.13
     информ
    0.13
     educator
    0.13
     informational
    0.13
    Activations Density 0.024%

    No Known Activations