© 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. 18303
    Prev
    Next
    INDEX
    Explanations

    belongs

    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
     સ્થિતિ
    -0.09
    .sqrt
    -0.08
     स्थिति
    -0.08
     influencing
    -0.08
     સતત
    -0.07
     inducing
    -0.07
    .reset
    -0.07
    筋
    -0.07
     concreto
    -0.07
    ಿಂಗ್
    -0.07
    POSITIVE LOGITS
     принад
    0.25
     принадлеж
    0.24
     предназнач
    0.24
     belonged
    0.22
     belong
    0.22
    属于
    0.21
     belongs
    0.21
     pertenc
    0.21
     pertenec
    0.21
     pertence
    0.20
    Activations Density 0.073%

    No Known Activations