© 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. 102419
    Prev
    Next
    INDEX
    Explanations

    R words

    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
     involucr
    -0.09
     located
    -0.08
     inflammation
    -0.08
     baisse
    -0.08
     Located
    -0.08
     proteins
    -0.08
     ubicado
    -0.08
     lact
    -0.08
     porod
    -0.08
     pleg
    -0.08
    POSITIVE LOGITS
    R
    0.15
    Rm
    0.12
    RC
    0.11
    Receiver
    0.11
     receptor
    0.11
    RB
    0.11
    RD
    0.11
    RW
    0.11
    RM
    0.11
    Rs
    0.10
    Activations Density 0.002%

    No Known Activations