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. 15-RESID-POST-AA
    6. 19264
    Prev
    Next
    INDEX
    Explanations

    hairstyles

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucl
    -0.09
    ദേശ
    -0.08
    博彩
    -0.08
     федераль
    -0.08
    自治
    -0.08
    -0.08
     operative
    -0.08
     incontro
    -0.08
     ioctl
    -0.08
     законодатель
    -0.07
    POSITIVE LOGITS
     hairstyle
    0.11
     गाँ
    0.10
     neatly
    0.09
     tidy
    0.09
     bébé
    0.09
     tucked
    0.09
     esconder
    0.09
     bebé
    0.09
     hairstyles
    0.09
     constructions
    0.09
    Activations Density 0.010%

    No Known Activations