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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95897
    Prev
    Next
    INDEX
    Explanations

    not

    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
     mighty
    -0.08
    <>();↵
    -0.08
    ая
    -0.08
     renowned
    -0.07
     hát
    -0.07
     lesser
    -0.07
     प्रतिष्ठ
    -0.07
     valor
    -0.07
     inclination
    -0.07
     preferencias
    -0.07
    POSITIVE LOGITS
    Lit
    0.08
    Hex
    0.08
    部署
    0.08
     écrit
    0.08
     соответствует
    0.07
    Lf
    0.07
     dressed
    0.07
    িজ
    0.07
    skosten
    0.07
    .datasets
    0.07
    Activations Density 0.081%

    No Known Activations