© 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. 29707
    Prev
    Next
    INDEX
    Explanations

    .status

    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
     이루
    -0.08
    amanya
    -0.07
     cé
    -0.07
     tidy
    -0.07
     мира
    -0.07
    ból
    -0.07
     було
    -0.07
     miễn
    -0.07
     কেউ
    -0.07
     мир
    -0.07
    POSITIVE LOGITS
     attrib
    0.08
     attraktiv
    0.08
                        ↵
    0.08
    			↵
    0.08
     conditioning
    0.08
     daya
    0.08
     burners
    0.08
     contribut
    0.08
     calorie
    0.08
    YT
    0.08
    Activations Density 0.001%

    No Known Activations