© 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. 23-RESID-POST-AA
    11. 96587
    Prev
    Next
    INDEX
    Explanations

    immediately

    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
    inned
    -0.09
     exactamente
    -0.09
     هنوز
    -0.09
     এখনও
    -0.09
    orma
    -0.08
     exatamente
    -0.08
    ualmente
    -0.08
     exactement
    -0.08
    awsze
    -0.08
    ualquier
    -0.08
    POSITIVE LOGITS
     gratification
    0.14
    iatamente
    0.13
     aftermath
    0.12
     vicinity
    0.12
     upon
    0.12
    aneously
    0.11
    Upon
    0.11
    anément
    0.11
     postpartum
    0.11
    ánea
    0.10
    Activations Density 0.021%

    No Known Activations