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. 65218
    Prev
    Next
    INDEX
    Explanations

    Commerce and purchasing

    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
     alde
    -0.08
     numer
    -0.08
     vuestro
    -0.08
     podrás
    -0.07
     orientar
    -0.07
    وان
    -0.07
     Ausbildungs
    -0.07
    щество
    -0.07
     vocês
    -0.07
     who's
    -0.07
    POSITIVE LOGITS
     preference
    0.10
    _preferences
    0.09
     tercih
    0.09
     koopt
    0.08
    _other
    0.08
     Anbieter
    0.08
     providers
    0.08
    .other
    0.08
     hesitant
    0.08
     Preference
    0.08
    Activations Density 0.065%

    No Known Activations