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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18805
    Prev
    Next
    INDEX
    Explanations

    Code using scanner

    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
     χρήση
    -0.08
    ostream
    -0.08
     UIStoryboard
    -0.07
    unist
    -0.07
     digno
    -0.07
     Receipt
    -0.07
     Transpar
    -0.07
    现金
    -0.07
     malloc
    -0.07
    ◎
    -0.07
    POSITIVE LOGITS
     அவர்
    0.09
    .next
    0.09
     حالی
    0.09
    ,next
    0.08
     akwai
    0.08
     தெரிவித்துள்ளார்
    0.08
    {sup
    0.08
     liebsten
    0.08
     अगले
    0.08
    ોજ
    0.08
    Activations Density 0.002%

    No Known Activations