© 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. 19-RESID-POST-AA
    11. 18633
    Prev
    Next
    INDEX
    Explanations

    Interest rates and percentages

    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
    ำน
    -0.10
    ാന്ത
    -0.09
    აწილ
    -0.09
     ถ่ายทอดสด
    -0.09
    ayanan
    -0.09
     പഞ്ചായത്ത്
    -0.09
     แมน
    -0.09
    construct
    -0.09
    apatan
    -0.09
    აპირ
    -0.08
    POSITIVE LOGITS
    TION
    0.08
    (context
    0.07
    .context
    0.07
     flown
    0.07
     deux
    0.07
     retard
    0.07
    0.07
     context
    0.07
    _CONTEXT
    0.07
     وبعد
    0.07
    Activations Density 0.000%
    No Known Activations