© 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. 18569
    Prev
    Next
    INDEX
    Explanations

    Ratios and scaling

    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
     sum
    -0.10
    �
    -0.09
    sum
    -0.09
     lastname
    -0.09
    开奖号
    -0.09
    提交
    -0.08
     minus
    -0.08
     Sum
    -0.08
    Sum
    -0.08
    _sum
    -0.08
    POSITIVE LOGITS
     scaling
    0.20
     Scaling
    0.19
    Scaling
    0.19
     ratios
    0.19
    Ratio
    0.18
     ratio
    0.18
     Ratio
    0.17
    _ratio
    0.17
    ratio
    0.17
     scalability
    0.16
    Activations Density 0.075%

    No Known Activations