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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6181
    Prev
    Next
    INDEX
    Explanations

    .com

    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
    ITable
    -0.08
    Finalmente
    -0.08
    iële
    -0.07
    Equation
    -0.07
    主义
    -0.07
    वाद
    -0.07
     вещей
    -0.07
    aceae
    -0.07
    -moving
    -0.07
    655
    -0.07
    POSITIVE LOGITS
    .au
    0.20
    .ua
    0.18
    /fwlink
    0.18
     वेबसाइट
    0.17
    .br
    0.16
    .uk
    0.16
    ,www
    0.15
     сайты
    0.15
    .my
    0.15
    /blog
    0.15
    Activations Density 0.049%

    No Known Activations