© 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. 21940
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Increment
    -0.08
    _increment
    -0.08
     increments
    -0.08
    Increment
    -0.08
    .increment
    -0.08
    .execution
    -0.08
     crt
    -0.08
    crements
    -0.08
    ，全
    -0.08
     مشتر
    -0.08
    POSITIVE LOGITS
     repell
    0.22
     repel
    0.20
     waterproof
    0.16
     water
    0.15
     Waterproof
    0.14
    rophobic
    0.14
     wett
    0.14
     hyd
    0.13
    拒
    0.13
     rep
    0.13
    Activations Density 0.010%

    No Known Activations