© 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. 18310
    Prev
    Next
    INDEX
    Explanations

    pressure

    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
     certain
    -0.08
     award
    -0.08
     everything
    -0.08
    leigh
    -0.08
    ization
    -0.08
     some
    -0.07
    ISTIC
    -0.07
    圣
    -0.07
    aksud
    -0.07
    apper
    -0.07
    POSITIVE LOGITS
     readings
    0.12
     DROP
    0.10
     medications
    0.10
     regulation
    0.10
     values
    0.10
    下降
    0.10
     hypertension
    0.10
     monitoring
    0.10
     medication
    0.10
    値
    0.09
    Activations Density 0.007%

    No Known Activations