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. 76639
    Prev
    Next
    INDEX
    Explanations

    any

    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
     Warm
    -0.08
     warm
    -0.08
     Contacts
    -0.08
     romana
    -0.08
     contacto
    -0.07
     recorded
    -0.07
    _contacts
    -0.07
    .contact
    -0.07
    Warm
    -0.07
     warme
    -0.07
    POSITIVE LOGITS
     limitless
    0.09
     suficientes
    0.09
     avancer
    0.09
     erreich
    0.09
     rendelkez
    0.08
     задачи
    0.08
     पर्याप्त
    0.08
    crire
    0.08
     adequately
    0.08
    limitations
    0.08
    Activations Density 0.001%

    No Known Activations