© 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. 18652
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     and
    -0.11
    .↵
    -0.11
     și
    -0.10
     आणि
    -0.10
    ുകയും
    -0.10
    ，但
    -0.10
     и
    -0.10
     และ
    -0.10
    	and
    -0.10
     ਅਤੇ
    -0.10
    POSITIVE LOGITS
     we
    0.16
     আমরা
    0.13
     આપણે
    0.13
     ನಾವು
    0.13
     let's
    0.13
     teremos
    0.13
     અમે
    0.13
     imamo
    0.13
     temos
    0.12
     אנחנו
    0.12
    Activations Density 0.031%

    No Known Activations