© 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. 103245
    Prev
    Next
    INDEX
    Explanations

    if

    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
     have
    -0.10
     avoir
    -0.10
     has
    -0.09
     would
    -0.09
     pokud
    -0.09
    _if
    -0.09
     abbia
    -0.09
     durumda
    -0.09
    _has
    -0.08
    )
    -0.08
    POSITIVE LOGITS
     there's
    0.15
     we're
    0.15
     it's
    0.14
     we
    0.14
     they're
    0.14
     everything
    0.13
     they
    0.13
    everything
    0.12
     մենք
    0.11
     there
    0.11
    Activations Density 0.026%

    No Known Activations