© 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. 75
    Prev
    Next
    INDEX
    Explanations

    iconic

    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
    gebouw
    -0.08
     lil
    -0.08
    ontwikkeling
    -0.08
    -sided
    -0.08
     ZA
    -0.08
    .Model
    -0.08
     Currently
    -0.08
     Bahasa
    -0.08
     বর্তমানে
    -0.08
    verband
    -0.08
    POSITIVE LOGITS
     berühm
    0.09
     famous
    0.09
     célèbre
    0.09
     renowned
    0.09
     repert
    0.08
     famed
    0.08
     famoso
    0.08
     hallmark
    0.08
     célè
    0.08
     iconic
    0.08
    Activations Density 0.003%

    No Known Activations