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. 11-RESID-POST-AA
    6. 65127
    Prev
    Next
    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lunes
    -0.09
    rale
    -0.08
    lunes
    -0.08
     בסיס
    -0.08
     اینکه
    -0.08
     alcal
    -0.08
     unary
    -0.08
     ઓછ
    -0.07
     LDL
    -0.07
     Δη
    -0.07
    POSITIVE LOGITS
     assures
    0.10
     वि�
    0.09
     forgiveness
    0.08
     खिल
    0.08
     forgive
    0.08
    Forg
    0.08
    thanks
    0.08
    ورت
    0.08
     विक
    0.08
     سبحانه
    0.08
    Activations Density 0.022%

    No Known Activations