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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18443
    Prev
    Next
    INDEX
    Explanations

    suffer

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     //
    -0.07
     needs
    -0.07
     يتعلق
    -0.07
     الأزمة
    -0.07
     kebutuhan
    -0.07
    izona
    -0.07
    onnement
    -0.07
    otics
    -0.07
    needs
    -0.07
     ihtiyaç
    -0.07
    POSITIVE LOGITS
     from
    0.16
    จาก
    0.15
    	from
    0.14
    _FROM
    0.13
     dari
    0.13
     از
    0.13
    _from
    0.12
     från
    0.12
    from
    0.12
     From
    0.12
    Activations Density 0.005%

    No Known Activations