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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 120310
    Prev
    Next
    INDEX
    Explanations

    uniqueness and differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poj
    -0.07
    larından
    -0.07
    Rounds
    -0.07
     Pound
    -0.07
    ámica
    -0.07
     defamatory
    -0.07
     epochs
    -0.07
    �
    -0.07
     STEM
    -0.07
     soll
    -0.07
    POSITIVE LOGITS
     individualized
    0.12
     تختلف
    0.12
     individuell
    0.11
     individuellen
    0.11
     tailor
    0.11
     unieke
    0.11
     уник
    0.11
    unique
    0.11
     unique
    0.11
     индивиду
    0.11
    Activations Density 0.077%

    No Known Activations