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. 12042
    Prev
    Next
    INDEX
    Explanations

    can

    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
     Riv
    -0.08
     Troy
    -0.08
     Customize
    -0.08
     Rhe
    -0.08
     Prague
    -0.08
    крет
    -0.07
     Beirut
    -0.07
     liever
    -0.07
    ечного
    -0.07
     Grimm
    -0.07
    POSITIVE LOGITS
    �
    0.09
     erhöhen
    0.08
    extended
    0.08
     vaz
    0.08
     darstellen
    0.08
     Verfügung
    0.08
     entail
    0.08
     shout
    0.08
    出的
    0.08
    Extended
    0.07
    Activations Density 0.150%

    No Known Activations