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. 65503
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     ಮಹ
    -0.08
    伟
    -0.08
     ώρα
    -0.08
     tijd
    -0.08
     Ember
    -0.07
    Bright
    -0.07
    バー
    -0.07
     Вар
    -0.07
     tiempo
    -0.07
     temps
    -0.07
    POSITIVE LOGITS
    ,因此
    0.08
    roe
    0.08
    upuk
    0.07
    พิ
    0.07
    იკული
    0.07
    091
    0.07
    572
    0.07
     specie
    0.07
    bea
    0.07
    шылық
    0.07
    Activations Density 0.169%

    No Known Activations