© 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. 23-RESID-POST-AA
    11. 50340
    Prev
    Next
    INDEX
    Explanations

    Overdue payments

    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
     expend
    -0.07
     symmetry
    -0.07
    -0.07
     symmetrical
    -0.07
     costa
    -0.07
     gewinnen
    -0.07
     köpa
    -0.07
     名人
    -0.07
     recrutement
    -0.07
    Peripheral
    -0.07
    POSITIVE LOGITS
     overdue
    0.24
     delin
    0.23
     задолж
    0.22
     payment
    0.20
     late
    0.19
     neach
    0.19
     payments
    0.18
    payment
    0.18
     betalings
    0.18
     unpaid
    0.18
    Activations Density 0.070%
    No Known Activations