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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48160
    Prev
    Next
    INDEX
    Explanations

    Prominence

    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
     edasi
    -0.08
     unknow
    -0.08
     inflater
    -0.08
     hydrocar
    -0.08
    未知
    -0.07
    泉
    -0.07
     szab
    -0.07
    输了
    -0.07
     piir
    -0.07
     writings
    -0.07
    POSITIVE LOGITS
     prominent
    0.31
     prominently
    0.29
     prominence
    0.26
     promin
    0.23
     consp
    0.21
     opvall
    0.19
    Prom
    0.19
     visible
    0.19
     noticeable
    0.19
     Prom
    0.18
    Activations Density 0.047%

    No Known Activations