© 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. 18241
    Prev
    Next
    INDEX
    Explanations

    text

    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
    Repeated
    -0.08
     fator
    -0.08
    STITUTE
    -0.08
     Directorate
    -0.08
     Direct
    -0.08
     علوم
    -0.08
     مصادر
    -0.07
     قانون
    -0.07
     حافظ
    -0.07
    _SYSTEM
    -0.07
    POSITIVE LOGITS
    -based
    0.17
    -only
    0.12
    -render
    0.12
    -click
    0.12
    -to
    0.11
    -gener
    0.11
    -Based
    0.11
    -output
    0.11
    опис
    0.11
    -description
    0.11
    Activations Density 0.006%

    No Known Activations