© 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. 18614
    Prev
    Next
    INDEX
    Explanations

    conservative

    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
    étique
    -0.08
    ીત
    -0.08
    ingos
    -0.08
    τήσεις
    -0.08
    ée
    -0.08
    niques
    -0.08
    ibility
    -0.07
    ütte
    -0.07
     ehr
    -0.07
    άνι
    -0.07
    POSITIVE LOGITS
     estimates
    0.14
     estimate
    0.13
     Estimates
    0.12
    estimate
    0.12
    估
    0.11
     Estimate
    0.11
    Estimate
    0.11
     estimating
    0.11
     estimation
    0.10
     estimated
    0.10
    Activations Density 0.005%

    No Known Activations