© 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. 19-RESID-POST-AA
    11. 103178
    Prev
    Next
    INDEX
    Explanations

    the

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     têm
    -0.09
     certain
    -0.09
    .↵↵
    -0.09
    _one
    -0.08
     although
    -0.08
    :
    -0.08
    :#
    -0.08
    .
    -0.08
    082
    -0.08
     because
    -0.08
    POSITIVE LOGITS
     rest
    0.29
     remainder
    0.25
     overige
    0.24
     resto
    0.23
     reste
    0.23
     restante
    0.23
     übr
    0.23
    rest
    0.22
     restant
    0.22
     remaining
    0.21
    Activations Density 0.021%

    No Known Activations