© 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. 49709
    Prev
    Next
    INDEX
    Explanations

    Power Converters

    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
     judgment
    -0.09
     judgement
    -0.09
    هاز
    -0.09
     amper
    -0.08
     corrosion
    -0.08
     عورت
    -0.08
     jugement
    -0.08
     افغان
    -0.08
     conditional
    -0.08
     عمان
    -0.08
    POSITIVE LOGITS
     Full
    0.13
    -sw
    0.11
    Full
    0.11
    _sw
    0.11
     full
    0.10
     topology
    0.10
     Buck
    0.10
     Fuller
    0.10
     buck
    0.10
     LLC
    0.10
    Activations Density 0.007%

    No Known Activations