© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 69077
    Prev
    Next
    INDEX
    Explanations

    Temporal/conditional prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thats
    -0.08
     Jpa
    -0.08
     Then
    -0.08
     (=
    -0.08
     magen
    -0.07
    That's
    -0.07
    -0.07
     taut
    -0.07
    CW
    -0.07
     fudge
    -0.07
    POSITIVE LOGITS
    而言
    0.09
    <|endoftext|>
    0.08
    不断
    0.08
     demikian
    0.08
     expertly
    0.08
     setbacks
    0.08
    一些
    0.07
    कि
    0.07
     الرغم
    0.07
     rehabilitation
    0.07
    Activations Density 0.066%

    No Known Activations