© 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. 24581
    Prev
    Next
    INDEX
    Explanations

    .

    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
    �
    -0.08
    iguar
    -0.07
     resc
    -0.07
     ips
    -0.07
     rehe
    -0.07
     prel
    -0.07
    植
    -0.07
     propor
    -0.07
    Leng
    -0.07
     Corinth
    -0.07
    POSITIVE LOGITS
     �
    0.11
     Panther
    0.08
    mpr
    0.08
     broom
    0.08
     SCM
    0.07
     Gilbert
    0.07
     braid
    0.07
    IMITER
    0.07
     ert
    0.07
     Dud
    0.07
    Activations Density 0.023%

    No Known Activations