© 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. 7-RESID-POST-AA
    11. 1405
    Prev
    Next
    INDEX
    Explanations

    体

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pigment
    -0.08
     hồi
    -0.08
     keel
    -0.08
     massages
    -0.08
     dorsal
    -0.08
    845
    -0.08
     maten
    -0.08
     dressing
    -0.08
     cono
    -0.08
    angal
    -0.08
    POSITIVE LOGITS
    �
    0.08
     parfaite
    0.08
    align
    0.07
    て
    0.07
    ූ
    0.07
     perfecta
    0.07
     �
    0.07
    制度
    0.07
     mere
    0.07
     perfect
    0.07
    Activations Density 0.001%

    No Known Activations