© 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. 23-RESID-POST-AA
    11. 51775
    Prev
    Next
    INDEX
    Explanations

    hor

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brachte
    -0.08
     الجنوبية
    -0.08
    ۱۴
    -0.08
    pske
    -0.08
     عليكم
    -0.08
    orsi
    -0.08
     pano
    -0.07
     brengen
    -0.07
    сьці
    -0.07
    ARDS
    -0.07
    POSITIVE LOGITS
    manageable
    0.08
     ක
    0.08
     αλλ
    0.08
     manageable
    0.07
     яг
    0.07
     tü
    0.07
     μονα
    0.07
     тот
    0.07
     IND
    0.07
    conc
    0.07
    Activations Density 0.000%

    No Known Activations