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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96768
    Prev
    Next
    INDEX
    Explanations

    Foreign words for skills

    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
    мис
    -0.08
     invál
    -0.08
    ieważ
    -0.08
    üten
    -0.08
    ائنا
    -0.08
    στε
    -0.07
    ��
    -0.07
     جهانی
    -0.07
    ائي
    -0.07
    .NORMAL
    -0.07
    POSITIVE LOGITS
     esprit
    0.14
     compétences
    0.14
    ’esprit
    0.13
    'esprit
    0.13
     capacité
    0.13
     habilidades
    0.13
     connaissances
    0.12
     capacités
    0.12
     senso
    0.12
     Es
    0.12
    Activations Density 0.029%

    No Known Activations