© 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. 95287
    Prev
    Next
    INDEX
    Explanations

    ang

    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
    conditioning
    -0.08
     تو
    -0.08
     Comparable
    -0.08
     bottles
    -0.08
     �
    -0.08
     resembling
    -0.08
    extended
    -0.08
     backside
    -0.08
     دود
    -0.08
     चाहिए
    -0.07
    POSITIVE LOGITS
     tris
    0.09
    -around
    0.08
    artisan
    0.07
    野
    0.07
    াকার
    0.07
     serr
    0.07
    围
    0.07
     autour
    0.07
    obr
    0.07
    ৰ
    0.07
    Activations Density 0.002%

    No Known Activations