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. 98242
    Prev
    Next
    INDEX
    Explanations

    fictional characters

    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
    Не
    -0.08
     جيڪو
    -0.08
    নীত
    -0.08
     fifth
    -0.08
     firm's
    -0.08
     الذي
    -0.08
    අ
    -0.07
    另
    -0.07
    шы
    -0.07
    Certificates
    -0.07
    POSITIVE LOGITS
     Dragon
    0.13
    Dragon
    0.12
     Butterfly
    0.12
     dragon
    0.11
     Pokémon
    0.11
     Snapdragon
    0.11
     Turtle
    0.11
     Naruto
    0.10
     Penguin
    0.10
     Bunny
    0.10
    Activations Density 0.018%

    No Known Activations