© 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 EvalsExportsAPI 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. 49631
    Prev
    Next
    INDEX
    Explanations

    ع

    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
     bb
    -0.09
    UMMY
    -0.08
    ummy
    -0.08
    bb
    -0.08
    atieven
    -0.08
    ifth
    -0.08
    ARP
    -0.07
    isations
    -0.07
    ials
    -0.07
     bain
    -0.07
    POSITIVE LOGITS
    زى
    0.19
    زز
    0.17
    كس
    0.12
    طي
    0.12
    نى
    0.11
    انى
    0.11
    اني
    0.11
    ترض
    0.11
    ادل
    0.10
    َد
    0.10
    Activations Density 0.001%

    No Known Activations