© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54827
    Prev
    Next
    INDEX
    Explanations

    rope

    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
     vant
    -0.09
    akin
    -0.09
    van
    -0.08
     pleasing
    -0.07
     ರಿಂದ
    -0.07
    -0.07
    Clinic
    -0.07
     conscientes
    -0.07
    مه
    -0.07
    para
    -0.07
    POSITIVE LOGITS
     Biod
    0.08
     Dig
    0.08
     đào
    0.08
     dura
    0.08
    houder
    0.08
     Ti
    0.08
    الي
    0.08
    anho
    0.08
    holder
    0.07
     restante
    0.07
    Activations Density 0.004%
    No Known Activations