© 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. 50233
    Prev
    Next
    INDEX
    Explanations

    permissibility

    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
    тенсив
    -0.10
    -Sm
    -0.08
     particularly
    -0.08
     توق
    -0.08
     īpa
    -0.08
     chegada
    -0.08
     imply
    -0.08
     peate
    -0.08
     verrass
    -0.08
     besonders
    -0.08
    POSITIVE LOGITS
     permissible
    0.26
     harmless
    0.25
     benign
    0.24
     legitimate
    0.23
    Allowed
    0.21
     permitted
    0.21
    合法
    0.20
     lawful
    0.20
     innoc
    0.20
     toegestaan
    0.20
    Activations Density 0.162%

    No Known Activations