© 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 EvalsExportsAPI 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. 49856
    Prev
    Next
    INDEX
    Explanations

    Calend

    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
    번째
    -0.09
     세
    -0.09
     zabo
    -0.08
     صحيح
    -0.08
     данным
    -0.08
    점을
    -0.08
     حالت
    -0.08
    clam
    -0.08
    들과
    -0.07
    unt
    -0.07
    POSITIVE LOGITS
    rier
    0.13
    riers
    0.11
    RI
    0.09
    rie
    0.09
    how
    0.09
    איך
    0.08
    RA
    0.08
    ljuč
    0.08
     implication
    0.08
    wi
    0.08
    Activations Density 0.000%

    No Known Activations