Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2370
    Prev
    Next
    INDEX
    Explanations

    USB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
     că
    -0.08
    ıştır
    -0.08
     učen
    -0.07
     tú
    -0.07
     hob
    -0.07
    Cit
    -0.07
     જ
    -0.07
     ingenu
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Hu
    0.09
     Vr
    0.08
     ah
    0.08
     Ven
    0.08
     Vap
    0.08
     Wedding
    0.08
     Chen
    0.07
    ع
    0.07
     Edel
    0.07
     сиг
    0.07
    Activations Density 0.003%

    No Known Activations