© 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. 23-RESID-POST-AA
    11. 5561
    Prev
    Next
    INDEX
    Explanations

    say places of business

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organs
    -0.08
     Sint
    -0.08
     fiet
    -0.08
     zel
    -0.07
    _CART
    -0.07
     Nek
    -0.07
     synt
    -0.07
     patolog
    -0.07
     álbum
    -0.07
    amber
    -0.07
    POSITIVE LOGITS
     конферен
    0.17
     conference
    0.17
     переговор
    0.17
     सम्मेलन
    0.16
    会议
    0.16
     conférence
    0.15
     Conference
    0.15
     மாந
    0.15
     board
    0.14
    董事
    0.14
    Activations Density 0.038%

    No Known Activations