© 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. 51657
    Prev
    Next
    INDEX
    Explanations

    early or late

    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
     total
    -0.09
     Δ
    -0.09
     તમામ
    -0.09
     tüm
    -0.09
     π
    -0.09
     ratios
    -0.08
     ټول
    -0.08
     configurations
    -0.08
    帖
    -0.08
     $\
    -0.08
    POSITIVE LOGITS
     late
    0.15
    early
    0.14
    Early
    0.14
    late
    0.13
     early
    0.13
    Late
    0.13
     miaka
    0.13
     молодой
    0.12
     Late
    0.12
     อายุ
    0.12
    Activations Density 0.018%

    No Known Activations