© 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. 49089
    Prev
    Next
    INDEX
    Explanations

    short strings

    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
    BQ
    -0.08
    xbe
    -0.08
    IGH
    -0.08
    ūs
    -0.08
     Aq
    -0.08
    AQ
    -0.07
    _my
    -0.07
    uo
    -0.07
    Unsafe
    -0.07
    ��
    -0.07
    POSITIVE LOGITS
     mu
    0.09
     ini
    0.09
     j
    0.08
     ieu
    0.08
     Lob
    0.08
     okub
    0.08
     beta
    0.08
     J
    0.08
    \E
    0.08
     Mu
    0.08
    Activations Density 0.024%

    No Known Activations