© 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. 1021
    Prev
    Next
    INDEX
    Explanations

    Complete sentences

    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
    Win
    -0.09
    .azure
    -0.08
     curious
    -0.08
    做人
    -0.08
     Win
    -0.08
    win
    -0.07
     twilight
    -0.07
     thy
    -0.07
    .Win
    -0.07
    estin
    -0.07
    POSITIVE LOGITS
     remed
    0.12
     remedy
    0.10
     remedies
    0.10
     Remedy
    0.10
     behoefte
    0.10
     Remedies
    0.09
     addressed
    0.09
     remediation
    0.09
     ùn
    0.08
     respite
    0.08
    Activations Density 0.274%

    No Known Activations