© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16283
    Prev
    Next
    INDEX
    Explanations

    approaching

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     орт
    -0.07
     news
    -0.07
     diary
    -0.07
     ramai
    -0.07
     seca
    -0.07
     coh
    -0.07
     médi
    -0.07
     lenses
    -0.07
    .news
    -0.07
     =================================================================
    -0.06
    POSITIVE LOGITS
     unatt
    0.12
     nearing
    0.12
     approaching
    0.12
     ancak
    0.11
     gradually
    0.11
     fakat
    0.11
     가까
    0.11
     નજીક
    0.10
     предел
    0.10
    never
    0.10
    Activations Density 0.014%

    No Known Activations