© 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. 47584
    Prev
    Next
    INDEX
    Explanations

    Bo

    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
     vô
    -0.09
     fazê
    -0.08
     vwar
    -0.08
    primer
    -0.08
     primer
    -0.08
     platos
    -0.08
     пяти
    -0.08
     الخامس
    -0.08
    РА
    -0.07
     hacerlo
    -0.07
    POSITIVE LOGITS
    ehr
    0.09
    “In
    0.08
    .Namespace
    0.08
    Build
    0.08
    .Apply
    0.08
    Holding
    0.08
    .Weight
    0.08
    Sem
    0.07
    omi
    0.07
    оми
    0.07
    Activations Density 0.002%

    No Known Activations