© 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. 51893
    Prev
    Next
    INDEX
    Explanations

    ш

    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
    352
    -0.08
    504
    -0.08
     foul
    -0.08
    пион
    -0.07
     chronology
    -0.07
    734
    -0.07
    цент
    -0.07
    rm
    -0.07
    цуз
    -0.07
     hoops
    -0.07
    POSITIVE LOGITS
    مانية
    0.10
    есть
    0.10
    ість
    0.09
    ვიდ
    0.09
    venteen
    0.08
    irteen
    0.08
     Ms
    0.08
    ести
    0.08
     dva
    0.08
    ישה
    0.08
    Activations Density 0.001%

    No Known Activations