© 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. 23-RESID-POST-AA
    11. 50716
    Prev
    Next
    INDEX
    Explanations

    non-english languages

    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
    тың
    -0.17
    тің
    -0.16
    ‌സ്
    -0.14
    ’s
    -0.13
    ´s
    -0.12
    ‘s
    -0.12
    тердің
    -0.11
    тардың
    -0.11
    tt
    -0.11
    tijd
    -0.11
    POSITIVE LOGITS
    omething
    0.26
    phere
    0.24
    pecific
    0.24
    pective
    0.24
    cript
    0.23
    ystem
    0.23
    upport
    0.23
    cripts
    0.23
    pecies
    0.23
    pecial
    0.22
    Activations Density 0.859%

    No Known Activations