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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90963
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
     decoration
    -0.08
     kommen
    -0.08
    isio
    -0.07
    ident
    -0.07
    ys
    -0.07
     воспользоваться
    -0.07
     качестве
    -0.07
     喜
    -0.07
    knowledge
    -0.07
     decorations
    -0.07
    POSITIVE LOGITS
     relativa
    0.09
     Percent
    0.09
    નો
    0.09
     Abbott
    0.09
    Percent
    0.08
     misma
    0.08
     presa
    0.08
     కన్న
    0.08
     하나님
    0.08
     nueva
    0.08
    Activations Density 0.002%

    No Known Activations