© 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 EvalsExportsinterp-engineNEWAPI 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. 111466
    Prev
    Next
    INDEX
    Explanations

    unit conversion

    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
     Bened
    -0.09
     phr
    -0.08
    ستم
    -0.08
     retreats
    -0.08
     нест
    -0.08
     Zeich
    -0.07
    I'd
    -0.07
    afa
    -0.07
    ?!?!
    -0.07
    >{{$
    -0.07
    POSITIVE LOGITS
     occupants
    0.09
     habitaciones
    0.08
     болот
    0.08
     occupant
    0.07
     Millet
    0.07
     noq
    0.07
    parcel
    0.07
     seguidores
    0.07
     squat
    0.07
     dinero
    0.07
    Activations Density 0.013%

    No Known Activations