© 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. 23-RESID-POST-AA
    6. 49248
    Prev
    Next
    INDEX
    Explanations

    Spanish language

    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
     came
    -0.10
     come
    -0.10
    come
    -0.10
     Come
    -0.09
     coming
    -0.09
     comes
    -0.08
     trekken
    -0.08
    ac
    -0.08
    Come
    -0.08
     chegada
    -0.08
    POSITIVE LOGITS
     surge
    0.11
     parten
    0.10
     decor
    0.10
     tienen
    0.10
     décoration
    0.09
     Surge
    0.09
     decorrer
    0.09
     prov
    0.09
     imaju
    0.09
     teve
    0.09
    Activations Density 0.004%

    No Known Activations