© 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. 47794
    Prev
    Next
    INDEX
    Explanations

    C

    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
     мож
    -0.10
    adenas
    -0.09
    ueden
    -0.08
     Est
    -0.08
    287
    -0.08
    Aid
    -0.08
     aid
    -0.08
    252
    -0.07
    etik
    -0.07
     Great
    -0.07
    POSITIVE LOGITS
    ris
    0.14
    uscious
    0.09
    .R
    0.08
    rust
    0.08
    itr
    0.08
    aked
    0.08
    iger
    0.08
     crisp
    0.08
    rowned
    0.08
    руст
    0.08
    Activations Density 0.004%

    No Known Activations