© 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. 47354
    Prev
    Next
    INDEX
    Explanations

    between

    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
     Eintritt
    -0.08
    Vad
    -0.08
    מו
    -0.08
     richting
    -0.08
     출시
    -0.08
     పూర్త
    -0.08
    _RD
    -0.07
    DET
    -0.07
     выпуска
    -0.07
    -tail
    -0.07
    POSITIVE LOGITS
     વચ્ચે
    0.16
     ನಡುವೆ
    0.15
    之间
    0.15
     between
    0.14
     وبين
    0.14
     между
    0.14
     ನಡುವ
    0.12
     entre
    0.12
    between
    0.12
    _between
    0.12
    Activations Density 0.065%

    No Known Activations