© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47472
    Prev
    Next
    INDEX
    Explanations

    journalists

    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
     magma
    -0.08
     nat
    -0.08
    *↵
    -0.08
     counselling
    -0.07
     ukuf
    -0.07
    වත්
    -0.07
     ringing
    -0.07
     മുന്ന
    -0.07
    -frame
    -0.07
    ificada
    -0.07
    POSITIVE LOGITS
     oscuro
    0.09
     portrays
    0.08
    专题
    0.08
    を書く
    0.08
    搬
    0.08
    �
    0.08
     portrayed
    0.08
     portray
    0.08
    侠
    0.07
    �
    0.07
    Activations Density 0.042%

    No Known Activations