Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98648
    Prev
    Next
    INDEX
    Explanations

    fingers

    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
     boiler
    -0.08
     лагер
    -0.08
     Boilers
    -0.08
    леген
    -0.07
     പാർ
    -0.07
    irable
    -0.07
     helm
    -0.07
     boilers
    -0.07
    headline
    -0.07
     Roof
    -0.07
    POSITIVE LOGITS
     vingers
    0.28
     dedos
    0.27
     fingers
    0.26
     doigts
    0.26
     fingertips
    0.25
     finger
    0.25
     fingert
    0.24
     паль
    0.23
     fing
    0.22
     Finger
    0.21
    Activations Density 0.082%

    No Known Activations