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. 90240
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Professor
    -0.07
     efforts
    -0.07
    �
    -0.07
    pa
    -0.07
     verm
    -0.07
    Nick
    -0.07
     pa
    -0.07
    (pub
    -0.07
     NAS
    -0.07
     spas
    -0.07
    POSITIVE LOGITS
     нагруз
    0.08
    回事
    0.08
    шер
    0.08
    方式
    0.08
     повыс
    0.08
    itt
    0.08
    jeti
    0.08
    提高
    0.07
     인해
    0.07
    待
    0.07
    Activations Density 0.069%

    No Known Activations