© 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. 25068
    Prev
    Next
    INDEX
    Explanations

    qualifications

    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
     captain
    -0.07
     necesito
    -0.07
     ultimately
    -0.07
     denen
    -0.07
     episodio
    -0.07
     eventual
    -0.07
     urbana
    -0.07
     citizen
    -0.07
    Brit
    -0.07
     necesitamos
    -0.07
    POSITIVE LOGITS
     relaties
    0.08
    imum
    0.08
     सा
    0.08
    waż
    0.07
    heus
    0.07
     understatement
    0.07
    Caps
    0.07
     মনে
    0.07
     отношений
    0.07
    -pagination
    0.07
    Activations Density 0.000%

    No Known Activations