© 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. 11-RESID-POST-AA
    11. 95427
    Prev
    Next
    INDEX
    Explanations

    17

    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
    تا
    -0.08
    以下
    -0.08
     pronunciation
    -0.08
    语言
    -0.07
     E
    -0.07
     কোনও
    -0.07
     查
    -0.07
     esi
    -0.07
    anguages
    -0.07
    ർ
    -0.07
    POSITIVE LOGITS
     området
    0.08
    isaka
    0.08
     områ
    0.08
     watt
    0.08
    arella
    0.08
    iglie
    0.08
     apparaat
    0.08
     Automaten
    0.07
    IAA
    0.07
     fatores
    0.07
    Activations Density 0.039%

    No Known Activations