© 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. 5535
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
     existential
    -0.08
    _descriptor
    -0.07
     date
    -0.07
     appliance
    -0.07
    ဆ
    -0.07
     calorie
    -0.07
    ید
    -0.07
     existencia
    -0.07
    descriptor
    -0.07
     Converter
    -0.07
    POSITIVE LOGITS
    Rsp
    0.09
     TPS
    0.09
    TPS
    0.09
    KES
    0.08
     LVS
    0.08
     reprez
    0.08
     praw
    0.08
     Pvt
    0.08
    SPR
    0.08
     franchises
    0.08
    Activations Density 0.001%

    No Known Activations