© 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. 11-RESID-POST-AA
    11. 45588
    Prev
    Next
    INDEX
    Explanations

    downloads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _OCCURRED
    -0.09
    awake
    -0.09
     miser
    -0.08
     jacuzzi
    -0.08
     gymnastics
    -0.08
     ilumin
    -0.08
     awake
    -0.08
     akibat
    -0.08
    unin
    -0.08
     Ahnung
    -0.08
    POSITIVE LOGITS
     डाउनलोड
    0.22
    下载
    0.21
     다운로드
    0.20
     download
    0.19
     downloadable
    0.19
     Download
    0.19
     télécharger
    0.18
     下载
    0.18
    Download
    0.18
    .download
    0.18
    Activations Density 0.078%

    No Known Activations