© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 49116
    Prev
    Next
    INDEX
    Explanations

    hardening

    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
     Delete
    -0.07
     trash
    -0.07
    _DELETE
    -0.06
    贡
    -0.06
     deletion
    -0.06
    мещ
    -0.06
     delete
    -0.06
    /delete
    -0.06
     ilaq
    -0.06
    komm
    -0.06
    POSITIVE LOGITS
    固
    0.23
     curing
    0.23
     hard
    0.23
    硬
    0.22
     hardened
    0.21
     cured
    0.21
     solid
    0.21
     cure
    0.20
     cures
    0.20
    hard
    0.19
    Activations Density 0.047%

    No Known Activations