© 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. 91416
    Prev
    Next
    INDEX
    Explanations

    Spanish preposition "de"

    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
    999
    -0.07
     fal
    -0.07
     �
    -0.07
     الجم
    -0.07
     فر
    -0.07
    (vals
    -0.07
     हाल
    -0.07
    788
    -0.07
     magma
    -0.06
    Vals
    -0.06
    POSITIVE LOGITS
     trots
    0.09
     acordo
    0.09
    inition
    0.08
     invloed
    0.08
     ọma
    0.08
     acuerdo
    0.08
     اهمیت
    0.08
     maneras
    0.08
     طریق
    0.08
     manera
    0.08
    Activations Density 0.046%

    No Known Activations