© 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. 96423
    Prev
    Next
    INDEX
    Explanations

    catheters/urinary issues

    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
     mouv
    -0.08
     lati
    -0.08
    оборот
    -0.08
    ธ์
    -0.07
     identifies
    -0.07
     “‘
    -0.07
    ಂತ
    -0.07
    最後
    -0.07
     disrupted
    -0.07
     Consult
    -0.07
    POSITIVE LOGITS
    imation
    0.09
    ASS
    0.08
    ings
    0.08
    uscious
    0.08
    Leather
    0.08
    IMO
    0.08
    IGATION
    0.08
    imate
    0.08
    fn
    0.07
    uffs
    0.07
    Activations Density 0.000%

    No Known Activations