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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 97860
    Prev
    Next
    INDEX
    Explanations

    Romanian/English

    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
    istoire
    -0.08
     hov
    -0.08
     škole
    -0.08
    publique
    -0.07
     организации
    -0.07
     יכולים
    -0.07
     Sitzung
    -0.07
    izante
    -0.07
    Ville
    -0.07
     предприятия
    -0.07
    POSITIVE LOGITS
     functie
    0.12
     idee
    0.12
     valo
    0.12
    ţie
    0.12
     categorie
    0.11
     nevoie
    0.11
     relatie
    0.11
     cale
    0.10
     doua
    0.10
     masina
    0.10
    Activations Density 0.005%

    No Known Activations